SlideShare a Scribd company logo
From Back Testing to Live Trading
Vesna Straser, PhD
QuantCon, April 2016
Trade System Design Process
Trade Model and
System Design
•Evaluate signal
strength &
expected
alpha
•Check for
model
overfitting
•Check for look
ahead biases
•Optimize
system
parameters
Back Testing
•Conduct out-
of- sample
testing
•Check for data
consistency
•Evaluate
system risk
parameters
•Evaluate
position liquidity
•Use simplified
order fill and TC
models
Simulation / Paper
Trading
•Trade a
strategy using
tick data at
simulated
prices, trade
cost, and fill
rates
•Use market
simulator that
mirrors strategy
type
Live Trading
•Commit capital
to trade with
real market
data at actual
prices, fill rates,
and trade costs
Execution Testing Phase
Model Testing Phase
Performance Delta Between Back
Test, Simulation, and Live Trading
 Two sets of factors:
 Trade model / system specific → what and how much to trade
 Bad data, over-fitted model, poor out of sample performance
 Depends on signal research and modeling nuances
 Trade execution specific → how to trade
 Related to order fill assumptions: how orders are filled in terms of price, size,
and time
 Can be responsible for large discrepancies in trading performance
 High turnover strategies will tend to have greater discrepancies
Execution Factors Driving
Performance Delta
Back Testing Simulation Trading Live Trading
Data Structure OHLCV bar values
built from trade data
Bar or Tick Data
Market Depth
Level I Tick Data
Market Depth
Signal Calculation End of bar EOB or on every tick On every tick
Fill Price = f (order type) Fixed (OHLC) Simulated Market Driven
Fill Rate = f (order type) 100% Simulated ≤ 100% Market Driven ≤ 100%
Transaction Cost = f (order type) Fixed TC Model Market Driven
Trade Count = f (system settings) One trade per bar One or Market Driven Market Driven
Latency Not included Network Network and
Exchange
Strategy type and holding time
Example: One System, Two P&Ls
 Mean Reversion
System using 10
minutes time
interval
 Back Test stats:
o P&L: $188.5
o 6 trades
 Simulation stats:
o P&L: $112.5
o 5 trades
Trade did not
occur in Simulation
because entry
signal was not true
in real time
Sim Trade exited
at different time
due to real time
price dynamics
Sim Trade entry
price is higher
(worse) than
Back Test Price
Comparing Price Slippage
Actual Trade. Price
Decision Price
Simulation Trade Price
Slippage
Signal = True
Decision
Time
Price
TimeNext Bar
Open
BT Price Open
BT Price Close
Next Bar
Close
Bar 33 Bar 34 Bar 35 Bar 36 Bar 37
Comparing P&L Slippage
Next
Open
Entry
Time
Time
Next
Close
Next
Open
Next
Close
BT EnOP
BT EnCP
AEnP
ST EnP
Entry = True
Price
D EnP
BT ExOP
O P&L
ST ExP
S P&L
BT ExCP
C P&L
Exit
Time
Exit = True
D ExP
D P&L
Bar 33 Bar 34 Bar 35 Bar 36 Bar 37
AExP
A P&L
Timing Risk
Comparing Trade Count DynamicsPrice
Time
S P&L
Bar 33 Bar 34 Bar 35 Bar 36 Bar 37
A P&L
O P&L
C P&L
Exit = True
Trade 1
BT Trade 1
Entry = True Exit = True
D P%L
Entry = True
Trade 2
Understanding Back Testing
Limitations
 Signal is evaluated at the end of bar not intra-bar on every tick → lower/higher trade count
 Actual price movement within a bar is not known → which order gets filled first?
 Only one trade (entry or exit) per bar possible → lower trade count
 MO are filled at OC prices (user specified) → slippage
 LO are filled if limit price is within the HL range → 100% fill rate
 In case of multiple active limit orders BT engine may fill all limit orders → overfills?
 Inability to account for sudden price moves / gaps → higher fill rate or trade count
 Simplified fill model: based on trade prices only (vs bid/ask data) → lower spread cost
 100% fill rate if missing volume data → higher fill rate and lower market impact
 Slippage is incorporated as fixed rate (in ticks / cents) → imprecise market impact
 Missing network latency → higher fill rate and trade count
Improving Back Testing Accuracy
 Incorporate intra-bar price movement assumptions:
 If O is closer to H, assume O – H – L – C price move
 If O is closer to L or in the middle assume O – L – H – C
 Know which limit order gets filled first, “cancel” others
 Hybrid OHLC and tick data approach: add tick data replay for bars where signal is true
 Incorporate bid/ask data or spread to achieve more realistic fill price and spread cost
 Buy market orders are filled at ask prices
 Sell market orders are filled at bid prices
 Trade price closest to the decision time (e.g., O) would generate more accurate slippage
 If configurable, assume conservative fill model for limit orders (limit price vs HL)
 Incorporate Volume data to fine tune fill rate and market impact assumptions:
 Limit fill size to % of bar volume allowing for partial fills
 Make market impact model a function of relative order size: order size / bar volume
Understanding Simulation Trading
Limitations
 Signals are processed using OHLC or tick data (replayed or in real time) → Is the signal processing timing in sync with BT?
 Orders are processed using tick data but are filled per various order fill assumptions applied in market simulator
 Not all market simulators use level 2 data in simulating order fills (Interactive Brokers is using level 1 only)
 Order fill probability (price and size at which order is filled) is function of many dynamic variables:
 Order type: market, limit, stop, pegged
 Order size
 Bid/Ask volume = visible + hidden
 Market depth = visible + hidden
 Trade volume
 Time of day
 Place in queue = f (number of limit orders in the queue)
 Executing/routing exchange = f (liquidity, order processing latency, market conditions)
 Latency = f (network, broker, exchange, market conditions) → may cause missed trades in live trading
 Market conditions = f(volatility, trade rate, momentum, price gaps) → may cause missed trades in live trading
 Impact of limit orders on market depth changes is difficult to capture
Improving Simulation Trading
Accuracy
 Use realistic limit order fill assumptions, e.g., limit order is filled when trade price:
 touches a limit price → most liberal
 trades through the limit price
 trades through the limit price by X ticks → conservative
 touches the limit price X times, where X = f (place in queue) → most realistic
 fill price = Limit price → conservative
 fill price = Trade Price → liberal, assumes price improvement
 Market depth significantly improves accuracy of market order fill prices in case of partial fills
 Use bid/ask volume for a more realistic market order fill rate
 account for partial fills when order size > bid/ask size
 Use customizable transaction cost model = f (order size, side, spread, volume, depth,
volatility, horizon)
 Use dynamic latency model = f (real time network latency, avg exchange latency, avg
order processing latency)
Defining Strategy Holding Time
milliseconds seconds minutes hours days weeks
HIGH FREQUENCY
 HT = milliseconds to seconds
 Expected Profit < 1 spread
 Order size = very small
 Cost sensitivity: very high
 Trading concern = speed
 Strategy types:
 Latency arbitrage
 Statistical arbitrage
 Market making
 Pairs/spread trading
INTRA DAY
 HT = minutes to hours
 Expected profit = x * spread
 Order size = small
 Cost sensitivity: high
 Trading concern = spread
capture
 Strategy types:
 TA pattern following
 Momentum/Reversal
 Scalping
 News
LOW FREQUENCY
 HT = days to months
 Expected profit > 1%
 Order size = larger
 Cost sensitivity: moderate
 Trading concern = liquidity
 Strategy types:
 Long / Short
 Fundamental Factors
 Earnings quality
Back Testing and Simulation Model
Selection
HFT
INTRA DAY
LOW
FREQUENCY
 Back Testing = Simulation Model
 Use level 2 data
 Need custom built simulator; off the shelf
products do not capture sufficient details
 Custom TC model = f (trade strategy)
 Latency is critical
 Use O B/A based prices to fill market orders
 Apply intra-bar price move assumptions
 Use bar volume data
 Apply spread based TC model
 Use level 2 data
 Use conservative limit order fill model
 Apply small order TC model
 Account for latency
 Level 1 is sufficient, level 2 is better
 Apply order size limits
 Use complex order types (e.g., VWAP)
 Apply large (parent) order TC model
 Use conservative prices to fill orders, e.g.,
(H+L)/2, VWAP (if orders are large)
 Use bar volume data to limit order size or
estimate execution horizon
 Apply conservative TC assumptions
BACK TEST SIMULATION
Takeaways
1. Pick BT and ST provider that supports highest level of customizability for your
trading style
2. Know the nuances of the BT and ST platforms you are using
3. Pick data structure, fill model, and other settings that most closely match your
trading strategy
4. Assure consistency of data, order processing, and fill model assumptions
between BT and ST platforms vis a vis live trading
5. Use level 2 tick data in ST
6. Strategies with longer trading horizons and higher expected alpha will have
more accurate BT and ST results vis a vis live trading
7. Understand the specifics of the market structure of the products you are trading
(stocks vs futures vs FX vs options)
8. Stick to low turnover strategies, liquid trading universe, small order sizes, and be
conservative

More Related Content

What's hot

Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016
Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016
Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016
Quantopian
 
"A Framework-Based Approach to Building Quantitative Trading Systems" by Dr. ...
"A Framework-Based Approach to Building Quantitative Trading Systems" by Dr. ..."A Framework-Based Approach to Building Quantitative Trading Systems" by Dr. ...
"A Framework-Based Approach to Building Quantitative Trading Systems" by Dr. ...
Quantopian
 
Beware of Low Frequency Data by Ernie Chan, Managing Member, QTS Capital Mana...
Beware of Low Frequency Data by Ernie Chan, Managing Member, QTS Capital Mana...Beware of Low Frequency Data by Ernie Chan, Managing Member, QTS Capital Mana...
Beware of Low Frequency Data by Ernie Chan, Managing Member, QTS Capital Mana...
Quantopian
 
"Active Learning in Trading Algorithms" by David Fellah, Head of the EMEA Lin...
"Active Learning in Trading Algorithms" by David Fellah, Head of the EMEA Lin..."Active Learning in Trading Algorithms" by David Fellah, Head of the EMEA Lin...
"Active Learning in Trading Algorithms" by David Fellah, Head of the EMEA Lin...
Quantopian
 
A Guided Tour of Machine Learning for Traders by Tucker Balch at QuantCon 2016
A Guided Tour of Machine Learning for Traders by Tucker Balch at QuantCon 2016A Guided Tour of Machine Learning for Traders by Tucker Balch at QuantCon 2016
A Guided Tour of Machine Learning for Traders by Tucker Balch at QuantCon 2016
Quantopian
 
"Trading Strategies That Are Designed Not Fitted" by Robert Carver, Independe...
"Trading Strategies That Are Designed Not Fitted" by Robert Carver, Independe..."Trading Strategies That Are Designed Not Fitted" by Robert Carver, Independe...
"Trading Strategies That Are Designed Not Fitted" by Robert Carver, Independe...
Quantopian
 
"Deep Q-Learning for Trading" by Dr. Tucker Balch, Professor of Interactive C...
"Deep Q-Learning for Trading" by Dr. Tucker Balch, Professor of Interactive C..."Deep Q-Learning for Trading" by Dr. Tucker Balch, Professor of Interactive C...
"Deep Q-Learning for Trading" by Dr. Tucker Balch, Professor of Interactive C...
Quantopian
 
Automated Selection and Robustness for Systematic Trading Strategies by Dr. T...
Automated Selection and Robustness for Systematic Trading Strategies by Dr. T...Automated Selection and Robustness for Systematic Trading Strategies by Dr. T...
Automated Selection and Robustness for Systematic Trading Strategies by Dr. T...
Quantopian
 
Market Timing, Big Data, and Machine Learning by Xiao Qiao at QuantCon 2016
Market Timing, Big Data, and Machine Learning by Xiao Qiao at QuantCon 2016Market Timing, Big Data, and Machine Learning by Xiao Qiao at QuantCon 2016
Market Timing, Big Data, and Machine Learning by Xiao Qiao at QuantCon 2016
Quantopian
 
Yield Curve Trading Strategies
Yield Curve Trading Strategies Yield Curve Trading Strategies
Yield Curve Trading Strategies
Online Finance Academy
 
Quantitative Trading in Eurodollar Futures Market by Edith Mandel at QuantCon...
Quantitative Trading in Eurodollar Futures Market by Edith Mandel at QuantCon...Quantitative Trading in Eurodollar Futures Market by Edith Mandel at QuantCon...
Quantitative Trading in Eurodollar Futures Market by Edith Mandel at QuantCon...
Quantopian
 
Classification of quantitative trading strategies webinar ppt
Classification of quantitative trading strategies webinar pptClassification of quantitative trading strategies webinar ppt
Classification of quantitative trading strategies webinar ppt
QuantInsti
 
Algorithmic Trading: an Overview
Algorithmic Trading: an Overview Algorithmic Trading: an Overview
Algorithmic Trading: an Overview
EXANTE
 
How to design quant trading strategies using “R”?
How to design quant trading strategies using “R”?How to design quant trading strategies using “R”?
How to design quant trading strategies using “R”?
QuantInsti
 
Combining the Best Stock Selection Factors by Patrick O'Shaughnessy at QuantC...
Combining the Best Stock Selection Factors by Patrick O'Shaughnessy at QuantC...Combining the Best Stock Selection Factors by Patrick O'Shaughnessy at QuantC...
Combining the Best Stock Selection Factors by Patrick O'Shaughnessy at QuantC...
Quantopian
 
"From Trading Strategy to Becoming an Industry Professional – How to Break in...
"From Trading Strategy to Becoming an Industry Professional – How to Break in..."From Trading Strategy to Becoming an Industry Professional – How to Break in...
"From Trading Strategy to Becoming an Industry Professional – How to Break in...
Quantopian
 
Algo Trading
Algo TradingAlgo Trading
Algo Trading
Francesco Torraco
 
Algorithmic Trading
Algorithmic TradingAlgorithmic Trading
Algorithmic Trading
Alice Chan
 
"From Alpha Discovery to Portfolio Construction: Pitfalls and Solutions" by D...
"From Alpha Discovery to Portfolio Construction: Pitfalls and Solutions" by D..."From Alpha Discovery to Portfolio Construction: Pitfalls and Solutions" by D...
"From Alpha Discovery to Portfolio Construction: Pitfalls and Solutions" by D...
Quantopian
 

What's hot (20)

Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016
Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016
Should You Build Your Own Backtester? by Michael Halls-Moore at QuantCon 2016
 
"A Framework-Based Approach to Building Quantitative Trading Systems" by Dr. ...
"A Framework-Based Approach to Building Quantitative Trading Systems" by Dr. ..."A Framework-Based Approach to Building Quantitative Trading Systems" by Dr. ...
"A Framework-Based Approach to Building Quantitative Trading Systems" by Dr. ...
 
Beware of Low Frequency Data by Ernie Chan, Managing Member, QTS Capital Mana...
Beware of Low Frequency Data by Ernie Chan, Managing Member, QTS Capital Mana...Beware of Low Frequency Data by Ernie Chan, Managing Member, QTS Capital Mana...
Beware of Low Frequency Data by Ernie Chan, Managing Member, QTS Capital Mana...
 
"Active Learning in Trading Algorithms" by David Fellah, Head of the EMEA Lin...
"Active Learning in Trading Algorithms" by David Fellah, Head of the EMEA Lin..."Active Learning in Trading Algorithms" by David Fellah, Head of the EMEA Lin...
"Active Learning in Trading Algorithms" by David Fellah, Head of the EMEA Lin...
 
A Guided Tour of Machine Learning for Traders by Tucker Balch at QuantCon 2016
A Guided Tour of Machine Learning for Traders by Tucker Balch at QuantCon 2016A Guided Tour of Machine Learning for Traders by Tucker Balch at QuantCon 2016
A Guided Tour of Machine Learning for Traders by Tucker Balch at QuantCon 2016
 
"Trading Strategies That Are Designed Not Fitted" by Robert Carver, Independe...
"Trading Strategies That Are Designed Not Fitted" by Robert Carver, Independe..."Trading Strategies That Are Designed Not Fitted" by Robert Carver, Independe...
"Trading Strategies That Are Designed Not Fitted" by Robert Carver, Independe...
 
"Deep Q-Learning for Trading" by Dr. Tucker Balch, Professor of Interactive C...
"Deep Q-Learning for Trading" by Dr. Tucker Balch, Professor of Interactive C..."Deep Q-Learning for Trading" by Dr. Tucker Balch, Professor of Interactive C...
"Deep Q-Learning for Trading" by Dr. Tucker Balch, Professor of Interactive C...
 
Automated Selection and Robustness for Systematic Trading Strategies by Dr. T...
Automated Selection and Robustness for Systematic Trading Strategies by Dr. T...Automated Selection and Robustness for Systematic Trading Strategies by Dr. T...
Automated Selection and Robustness for Systematic Trading Strategies by Dr. T...
 
Market Timing, Big Data, and Machine Learning by Xiao Qiao at QuantCon 2016
Market Timing, Big Data, and Machine Learning by Xiao Qiao at QuantCon 2016Market Timing, Big Data, and Machine Learning by Xiao Qiao at QuantCon 2016
Market Timing, Big Data, and Machine Learning by Xiao Qiao at QuantCon 2016
 
Understanding Diagonal Spreads
Understanding Diagonal SpreadsUnderstanding Diagonal Spreads
Understanding Diagonal Spreads
 
Yield Curve Trading Strategies
Yield Curve Trading Strategies Yield Curve Trading Strategies
Yield Curve Trading Strategies
 
Quantitative Trading in Eurodollar Futures Market by Edith Mandel at QuantCon...
Quantitative Trading in Eurodollar Futures Market by Edith Mandel at QuantCon...Quantitative Trading in Eurodollar Futures Market by Edith Mandel at QuantCon...
Quantitative Trading in Eurodollar Futures Market by Edith Mandel at QuantCon...
 
Classification of quantitative trading strategies webinar ppt
Classification of quantitative trading strategies webinar pptClassification of quantitative trading strategies webinar ppt
Classification of quantitative trading strategies webinar ppt
 
Algorithmic Trading: an Overview
Algorithmic Trading: an Overview Algorithmic Trading: an Overview
Algorithmic Trading: an Overview
 
How to design quant trading strategies using “R”?
How to design quant trading strategies using “R”?How to design quant trading strategies using “R”?
How to design quant trading strategies using “R”?
 
Combining the Best Stock Selection Factors by Patrick O'Shaughnessy at QuantC...
Combining the Best Stock Selection Factors by Patrick O'Shaughnessy at QuantC...Combining the Best Stock Selection Factors by Patrick O'Shaughnessy at QuantC...
Combining the Best Stock Selection Factors by Patrick O'Shaughnessy at QuantC...
 
"From Trading Strategy to Becoming an Industry Professional – How to Break in...
"From Trading Strategy to Becoming an Industry Professional – How to Break in..."From Trading Strategy to Becoming an Industry Professional – How to Break in...
"From Trading Strategy to Becoming an Industry Professional – How to Break in...
 
Algo Trading
Algo TradingAlgo Trading
Algo Trading
 
Algorithmic Trading
Algorithmic TradingAlgorithmic Trading
Algorithmic Trading
 
"From Alpha Discovery to Portfolio Construction: Pitfalls and Solutions" by D...
"From Alpha Discovery to Portfolio Construction: Pitfalls and Solutions" by D..."From Alpha Discovery to Portfolio Construction: Pitfalls and Solutions" by D...
"From Alpha Discovery to Portfolio Construction: Pitfalls and Solutions" by D...
 

Viewers also liked

Dual Momentum Investing by Gary Antonacci QuantCon 2016
Dual Momentum Investing by Gary Antonacci QuantCon 2016Dual Momentum Investing by Gary Antonacci QuantCon 2016
Dual Momentum Investing by Gary Antonacci QuantCon 2016
Quantopian
 
A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...
A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...
A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...
Quantopian
 
Peculiarities of Volatilities by Ernest Chan at QuantCon 2016
Peculiarities of Volatilities by Ernest Chan at QuantCon 2016Peculiarities of Volatilities by Ernest Chan at QuantCon 2016
Peculiarities of Volatilities by Ernest Chan at QuantCon 2016
Quantopian
 
Trade Like a Chimp: Unleash Your Inner Primate by Andreas Clenow at QuantCon ...
Trade Like a Chimp: Unleash Your Inner Primate by Andreas Clenow at QuantCon ...Trade Like a Chimp: Unleash Your Inner Primate by Andreas Clenow at QuantCon ...
Trade Like a Chimp: Unleash Your Inner Primate by Andreas Clenow at QuantCon ...
Quantopian
 
Self-Directed Investing by Akhil Lodha, Co-founder of Sliced Investing, and M...
Self-Directed Investing by Akhil Lodha, Co-founder of Sliced Investing, and M...Self-Directed Investing by Akhil Lodha, Co-founder of Sliced Investing, and M...
Self-Directed Investing by Akhil Lodha, Co-founder of Sliced Investing, and M...
Quantopian
 
The Sustainable Active Investing Framework: Simple, but Not Easy by Wesley Gr...
The Sustainable Active Investing Framework: Simple, but Not Easy by Wesley Gr...The Sustainable Active Investing Framework: Simple, but Not Easy by Wesley Gr...
The Sustainable Active Investing Framework: Simple, but Not Easy by Wesley Gr...
Quantopian
 
Crowd-sourced Alpha: The Search for the Holy Grail of Investing
 Crowd-sourced Alpha: The Search for the Holy Grail of Investing Crowd-sourced Alpha: The Search for the Holy Grail of Investing
Crowd-sourced Alpha: The Search for the Holy Grail of Investing
Quantopian
 
Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...
Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...
Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...
Quantopian
 
Algorithmic Finance Meetup: Starmine Short Interest Talk
Algorithmic Finance Meetup: Starmine Short Interest Talk Algorithmic Finance Meetup: Starmine Short Interest Talk
Algorithmic Finance Meetup: Starmine Short Interest Talk
Quantopian
 
Estimates Too High, Low? Check the Calendar
Estimates Too High, Low?  Check the CalendarEstimates Too High, Low?  Check the Calendar
Estimates Too High, Low? Check the Calendar
Greg Harrison
 
Context Chat - why, what & how
Context Chat - why, what & howContext Chat - why, what & how
Context Chat - why, what & how
icemobile
 
Welcome to QuantCon 2016 John "fawce" Fawcett, Founder and CEO of Quantopian
Welcome to QuantCon 2016 John "fawce" Fawcett, Founder and CEO of QuantopianWelcome to QuantCon 2016 John "fawce" Fawcett, Founder and CEO of Quantopian
Welcome to QuantCon 2016 John "fawce" Fawcett, Founder and CEO of Quantopian
Quantopian
 
Trading Strategies Based on Market Impact of Macroeconomic Announcements by A...
Trading Strategies Based on Market Impact of Macroeconomic Announcementsby A...Trading Strategies Based on Market Impact of Macroeconomic Announcementsby A...
Trading Strategies Based on Market Impact of Macroeconomic Announcements by A...
Quantopian
 
Improving Predictability of Oil via Reuters News Text by Sameena Shah at Quan...
Improving Predictability of Oil via Reuters News Text by Sameena Shah at Quan...Improving Predictability of Oil via Reuters News Text by Sameena Shah at Quan...
Improving Predictability of Oil via Reuters News Text by Sameena Shah at Quan...
Quantopian
 
Needle in the Haystack by Anshul Vikram Pandey at QuantCon 2016
Needle in the Haystack by Anshul Vikram Pandey at QuantCon 2016Needle in the Haystack by Anshul Vikram Pandey at QuantCon 2016
Needle in the Haystack by Anshul Vikram Pandey at QuantCon 2016
Quantopian
 
Financial Engineering and Its Discontents by Emanuel Derman at QuantCon 2016
Financial Engineering and Its Discontents by Emanuel Derman at QuantCon 2016Financial Engineering and Its Discontents by Emanuel Derman at QuantCon 2016
Financial Engineering and Its Discontents by Emanuel Derman at QuantCon 2016
Quantopian
 
The Evolution of Social Listening for Capital Markets by Chris Camillo at Qua...
The Evolution of Social Listening for Capital Markets by Chris Camillo at Qua...The Evolution of Social Listening for Capital Markets by Chris Camillo at Qua...
The Evolution of Social Listening for Capital Markets by Chris Camillo at Qua...
Quantopian
 
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
Quantopian
 
Latency in Automated Trading Systems by Andrei Kirilenko at QuantCon 2016
Latency in Automated Trading Systems by Andrei Kirilenko at QuantCon 2016Latency in Automated Trading Systems by Andrei Kirilenko at QuantCon 2016
Latency in Automated Trading Systems by Andrei Kirilenko at QuantCon 2016
Quantopian
 
Meb Faber at QuantCon 2016
Meb Faber at QuantCon 2016Meb Faber at QuantCon 2016
Meb Faber at QuantCon 2016
Quantopian
 

Viewers also liked (20)

Dual Momentum Investing by Gary Antonacci QuantCon 2016
Dual Momentum Investing by Gary Antonacci QuantCon 2016Dual Momentum Investing by Gary Antonacci QuantCon 2016
Dual Momentum Investing by Gary Antonacci QuantCon 2016
 
A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...
A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...
A Vision for Quantitative Investing in the Data Economy by Michael Beal at Qu...
 
Peculiarities of Volatilities by Ernest Chan at QuantCon 2016
Peculiarities of Volatilities by Ernest Chan at QuantCon 2016Peculiarities of Volatilities by Ernest Chan at QuantCon 2016
Peculiarities of Volatilities by Ernest Chan at QuantCon 2016
 
Trade Like a Chimp: Unleash Your Inner Primate by Andreas Clenow at QuantCon ...
Trade Like a Chimp: Unleash Your Inner Primate by Andreas Clenow at QuantCon ...Trade Like a Chimp: Unleash Your Inner Primate by Andreas Clenow at QuantCon ...
Trade Like a Chimp: Unleash Your Inner Primate by Andreas Clenow at QuantCon ...
 
Self-Directed Investing by Akhil Lodha, Co-founder of Sliced Investing, and M...
Self-Directed Investing by Akhil Lodha, Co-founder of Sliced Investing, and M...Self-Directed Investing by Akhil Lodha, Co-founder of Sliced Investing, and M...
Self-Directed Investing by Akhil Lodha, Co-founder of Sliced Investing, and M...
 
The Sustainable Active Investing Framework: Simple, but Not Easy by Wesley Gr...
The Sustainable Active Investing Framework: Simple, but Not Easy by Wesley Gr...The Sustainable Active Investing Framework: Simple, but Not Easy by Wesley Gr...
The Sustainable Active Investing Framework: Simple, but Not Easy by Wesley Gr...
 
Crowd-sourced Alpha: The Search for the Holy Grail of Investing
 Crowd-sourced Alpha: The Search for the Holy Grail of Investing Crowd-sourced Alpha: The Search for the Holy Grail of Investing
Crowd-sourced Alpha: The Search for the Holy Grail of Investing
 
Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...
Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...
Case Studies in Creating Quant Models from Large Scale Unstructured Text by S...
 
Algorithmic Finance Meetup: Starmine Short Interest Talk
Algorithmic Finance Meetup: Starmine Short Interest Talk Algorithmic Finance Meetup: Starmine Short Interest Talk
Algorithmic Finance Meetup: Starmine Short Interest Talk
 
Estimates Too High, Low? Check the Calendar
Estimates Too High, Low?  Check the CalendarEstimates Too High, Low?  Check the Calendar
Estimates Too High, Low? Check the Calendar
 
Context Chat - why, what & how
Context Chat - why, what & howContext Chat - why, what & how
Context Chat - why, what & how
 
Welcome to QuantCon 2016 John "fawce" Fawcett, Founder and CEO of Quantopian
Welcome to QuantCon 2016 John "fawce" Fawcett, Founder and CEO of QuantopianWelcome to QuantCon 2016 John "fawce" Fawcett, Founder and CEO of Quantopian
Welcome to QuantCon 2016 John "fawce" Fawcett, Founder and CEO of Quantopian
 
Trading Strategies Based on Market Impact of Macroeconomic Announcements by A...
Trading Strategies Based on Market Impact of Macroeconomic Announcementsby A...Trading Strategies Based on Market Impact of Macroeconomic Announcementsby A...
Trading Strategies Based on Market Impact of Macroeconomic Announcements by A...
 
Improving Predictability of Oil via Reuters News Text by Sameena Shah at Quan...
Improving Predictability of Oil via Reuters News Text by Sameena Shah at Quan...Improving Predictability of Oil via Reuters News Text by Sameena Shah at Quan...
Improving Predictability of Oil via Reuters News Text by Sameena Shah at Quan...
 
Needle in the Haystack by Anshul Vikram Pandey at QuantCon 2016
Needle in the Haystack by Anshul Vikram Pandey at QuantCon 2016Needle in the Haystack by Anshul Vikram Pandey at QuantCon 2016
Needle in the Haystack by Anshul Vikram Pandey at QuantCon 2016
 
Financial Engineering and Its Discontents by Emanuel Derman at QuantCon 2016
Financial Engineering and Its Discontents by Emanuel Derman at QuantCon 2016Financial Engineering and Its Discontents by Emanuel Derman at QuantCon 2016
Financial Engineering and Its Discontents by Emanuel Derman at QuantCon 2016
 
The Evolution of Social Listening for Capital Markets by Chris Camillo at Qua...
The Evolution of Social Listening for Capital Markets by Chris Camillo at Qua...The Evolution of Social Listening for Capital Markets by Chris Camillo at Qua...
The Evolution of Social Listening for Capital Markets by Chris Camillo at Qua...
 
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
Honey, I Deep-shrunk the Sample Covariance Matrix! by Erk Subasi at QuantCon ...
 
Latency in Automated Trading Systems by Andrei Kirilenko at QuantCon 2016
Latency in Automated Trading Systems by Andrei Kirilenko at QuantCon 2016Latency in Automated Trading Systems by Andrei Kirilenko at QuantCon 2016
Latency in Automated Trading Systems by Andrei Kirilenko at QuantCon 2016
 
Meb Faber at QuantCon 2016
Meb Faber at QuantCon 2016Meb Faber at QuantCon 2016
Meb Faber at QuantCon 2016
 

Similar to From Backtesting to Live Trading by Vesna Straser at QuantCon 2016

MMT-04The-Algorithmic-Trading-Process.pdf
MMT-04The-Algorithmic-Trading-Process.pdfMMT-04The-Algorithmic-Trading-Process.pdf
MMT-04The-Algorithmic-Trading-Process.pdf
SiddharthKumar701604
 
Modeling Transaction Costs for Algorithmic Strategies
Modeling Transaction Costs for Algorithmic StrategiesModeling Transaction Costs for Algorithmic Strategies
Modeling Transaction Costs for Algorithmic Strategies
Quantopian
 
by Mark GoetschThe PiecesArbitr.docx
by Mark GoetschThe PiecesArbitr.docxby Mark GoetschThe PiecesArbitr.docx
by Mark GoetschThe PiecesArbitr.docx
humphrieskalyn
 
Algorithmic trading
Algorithmic tradingAlgorithmic trading
Algorithmic trading
Tushar Rathi
 
AlphaTrader Trading Platform Features
AlphaTrader Trading Platform FeaturesAlphaTrader Trading Platform Features
AlphaTrader Trading Platform Features
Nicolas VITALE
 
Predictive automated marginal trading technology pamtt part 1
Predictive automated marginal trading technology   pamtt part 1 Predictive automated marginal trading technology   pamtt part 1
Predictive automated marginal trading technology pamtt part 1 Yuri Martemianov
 
Affecting Market Efficiency by Increasing Speed of Order Matching Systems on ...
Affecting Market Efficiency by Increasing Speed of Order Matching Systems on ...Affecting Market Efficiency by Increasing Speed of Order Matching Systems on ...
Affecting Market Efficiency by Increasing Speed of Order Matching Systems on ...
Takanobu Mizuta
 
Algorithmic Trading and FIX Protocol
Algorithmic Trading and FIX ProtocolAlgorithmic Trading and FIX Protocol
Algorithmic Trading and FIX Protocol
EXANTE
 
Machine Learning Based Cryptocurrency Trading by Arshak Navruzyan at QuantCon...
Machine Learning Based Cryptocurrency Trading by Arshak Navruzyan at QuantCon...Machine Learning Based Cryptocurrency Trading by Arshak Navruzyan at QuantCon...
Machine Learning Based Cryptocurrency Trading by Arshak Navruzyan at QuantCon...
Quantopian
 
Exante algotrading
Exante algotradingExante algotrading
Exante algotrading
EXANTE
 
A Quantitative Case Study on the Impact of Transaction Cost in High-Frequency...
A Quantitative Case Study on the Impact of Transaction Cost in High-Frequency...A Quantitative Case Study on the Impact of Transaction Cost in High-Frequency...
A Quantitative Case Study on the Impact of Transaction Cost in High-Frequency...
Cognizant
 
CostPerform’s multidimensional costing function leads to improved profitability
CostPerform’s multidimensional costing function leads to improved profitabilityCostPerform’s multidimensional costing function leads to improved profitability
CostPerform’s multidimensional costing function leads to improved profitabilityBrian Plowman
 
gatheral_financialrisks_paris2014.pdf
gatheral_financialrisks_paris2014.pdfgatheral_financialrisks_paris2014.pdf
gatheral_financialrisks_paris2014.pdf
TomHardy96
 
Order Flow Imbalance Trading Algorithm
Order Flow Imbalance Trading AlgorithmOrder Flow Imbalance Trading Algorithm
Order Flow Imbalance Trading AlgorithmReed Jessen
 
Electronic Trading for Programmers
Electronic Trading for ProgrammersElectronic Trading for Programmers
Electronic Trading for Programmers
MathiasGaunard2
 
Sample Pattern Analysis Algorithm Technique
Sample Pattern Analysis Algorithm TechniqueSample Pattern Analysis Algorithm Technique
Sample Pattern Analysis Algorithm Technique
Index Strategy Advisors
 
About Nextware
About NextwareAbout Nextware
About NextwareSmith Kim
 
Empirical Analysis of Limit Order Books
Empirical Analysis of Limit Order BooksEmpirical Analysis of Limit Order Books
Empirical Analysis of Limit Order Books
QuantInsti
 

Similar to From Backtesting to Live Trading by Vesna Straser at QuantCon 2016 (20)

MMT-04The-Algorithmic-Trading-Process.pdf
MMT-04The-Algorithmic-Trading-Process.pdfMMT-04The-Algorithmic-Trading-Process.pdf
MMT-04The-Algorithmic-Trading-Process.pdf
 
Modeling Transaction Costs for Algorithmic Strategies
Modeling Transaction Costs for Algorithmic StrategiesModeling Transaction Costs for Algorithmic Strategies
Modeling Transaction Costs for Algorithmic Strategies
 
10.1.1.129.1408
10.1.1.129.140810.1.1.129.1408
10.1.1.129.1408
 
by Mark GoetschThe PiecesArbitr.docx
by Mark GoetschThe PiecesArbitr.docxby Mark GoetschThe PiecesArbitr.docx
by Mark GoetschThe PiecesArbitr.docx
 
Algorithmic trading
Algorithmic tradingAlgorithmic trading
Algorithmic trading
 
AlphaTrader Trading Platform Features
AlphaTrader Trading Platform FeaturesAlphaTrader Trading Platform Features
AlphaTrader Trading Platform Features
 
Predictive automated marginal trading technology pamtt part 1
Predictive automated marginal trading technology   pamtt part 1 Predictive automated marginal trading technology   pamtt part 1
Predictive automated marginal trading technology pamtt part 1
 
Affecting Market Efficiency by Increasing Speed of Order Matching Systems on ...
Affecting Market Efficiency by Increasing Speed of Order Matching Systems on ...Affecting Market Efficiency by Increasing Speed of Order Matching Systems on ...
Affecting Market Efficiency by Increasing Speed of Order Matching Systems on ...
 
Algorithmic Trading and FIX Protocol
Algorithmic Trading and FIX ProtocolAlgorithmic Trading and FIX Protocol
Algorithmic Trading and FIX Protocol
 
Machine Learning Based Cryptocurrency Trading by Arshak Navruzyan at QuantCon...
Machine Learning Based Cryptocurrency Trading by Arshak Navruzyan at QuantCon...Machine Learning Based Cryptocurrency Trading by Arshak Navruzyan at QuantCon...
Machine Learning Based Cryptocurrency Trading by Arshak Navruzyan at QuantCon...
 
Exante algotrading
Exante algotradingExante algotrading
Exante algotrading
 
A Quantitative Case Study on the Impact of Transaction Cost in High-Frequency...
A Quantitative Case Study on the Impact of Transaction Cost in High-Frequency...A Quantitative Case Study on the Impact of Transaction Cost in High-Frequency...
A Quantitative Case Study on the Impact of Transaction Cost in High-Frequency...
 
CostPerform’s multidimensional costing function leads to improved profitability
CostPerform’s multidimensional costing function leads to improved profitabilityCostPerform’s multidimensional costing function leads to improved profitability
CostPerform’s multidimensional costing function leads to improved profitability
 
Trade mind
Trade mindTrade mind
Trade mind
 
gatheral_financialrisks_paris2014.pdf
gatheral_financialrisks_paris2014.pdfgatheral_financialrisks_paris2014.pdf
gatheral_financialrisks_paris2014.pdf
 
Order Flow Imbalance Trading Algorithm
Order Flow Imbalance Trading AlgorithmOrder Flow Imbalance Trading Algorithm
Order Flow Imbalance Trading Algorithm
 
Electronic Trading for Programmers
Electronic Trading for ProgrammersElectronic Trading for Programmers
Electronic Trading for Programmers
 
Sample Pattern Analysis Algorithm Technique
Sample Pattern Analysis Algorithm TechniqueSample Pattern Analysis Algorithm Technique
Sample Pattern Analysis Algorithm Technique
 
About Nextware
About NextwareAbout Nextware
About Nextware
 
Empirical Analysis of Limit Order Books
Empirical Analysis of Limit Order BooksEmpirical Analysis of Limit Order Books
Empirical Analysis of Limit Order Books
 

More from Quantopian

Being open (source) in the traditionally secretive field of quant finance.
Being open (source) in the traditionally secretive field of quant finance.Being open (source) in the traditionally secretive field of quant finance.
Being open (source) in the traditionally secretive field of quant finance.
Quantopian
 
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
Quantopian
 
Tearsheet feedback webinar 10.10.18
Tearsheet feedback webinar 10.10.18Tearsheet feedback webinar 10.10.18
Tearsheet feedback webinar 10.10.18
Quantopian
 
"Three Dimensional Time: Working with Alternative Data" by Kathryn Glowinski,...
"Three Dimensional Time: Working with Alternative Data" by Kathryn Glowinski,..."Three Dimensional Time: Working with Alternative Data" by Kathryn Glowinski,...
"Three Dimensional Time: Working with Alternative Data" by Kathryn Glowinski,...
Quantopian
 
"Alpha from Alternative Data" by Emmett Kilduff, Founder and CEO of Eagle Alpha
"Alpha from Alternative Data" by Emmett Kilduff,  Founder and CEO of Eagle Alpha"Alpha from Alternative Data" by Emmett Kilduff,  Founder and CEO of Eagle Alpha
"Alpha from Alternative Data" by Emmett Kilduff, Founder and CEO of Eagle Alpha
Quantopian
 
"Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese...
"Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese..."Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese...
"Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese...
Quantopian
 
"Portfolio Optimisation When You Don’t Know the Future (or the Past)" by Rob...
"Portfolio Optimisation When You Don’t Know the Future (or the Past)" by Rob..."Portfolio Optimisation When You Don’t Know the Future (or the Past)" by Rob...
"Portfolio Optimisation When You Don’t Know the Future (or the Past)" by Rob...
Quantopian
 
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...
Quantopian
 
“Market Insights Through the Lens of a Risk Model” by Olivier d'Assier, Head ...
“Market Insights Through the Lens of a Risk Model” by Olivier d'Assier, Head ...“Market Insights Through the Lens of a Risk Model” by Olivier d'Assier, Head ...
“Market Insights Through the Lens of a Risk Model” by Olivier d'Assier, Head ...
Quantopian
 
"Maximize Alpha with Systematic Factor Testing" by Cheng Peng, Software Engin...
"Maximize Alpha with Systematic Factor Testing" by Cheng Peng, Software Engin..."Maximize Alpha with Systematic Factor Testing" by Cheng Peng, Software Engin...
"Maximize Alpha with Systematic Factor Testing" by Cheng Peng, Software Engin...
Quantopian
 
"How to Run a Quantitative Trading Business in China with Python" by Xiaoyou ...
"How to Run a Quantitative Trading Business in China with Python" by Xiaoyou ..."How to Run a Quantitative Trading Business in China with Python" by Xiaoyou ...
"How to Run a Quantitative Trading Business in China with Python" by Xiaoyou ...
Quantopian
 
"Fundamental Forecasts: Methods and Timing" by Vinesh Jha, CEO of ExtractAlpha
"Fundamental Forecasts: Methods and Timing" by Vinesh Jha, CEO of ExtractAlpha"Fundamental Forecasts: Methods and Timing" by Vinesh Jha, CEO of ExtractAlpha
"Fundamental Forecasts: Methods and Timing" by Vinesh Jha, CEO of ExtractAlpha
Quantopian
 
"Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Boo...
"Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Boo..."Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Boo...
"Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Boo...
Quantopian
 
"Making the Grade: A Look Inside the Algorithm Evaluation Process" by Dr. Jes...
"Making the Grade: A Look Inside the Algorithm Evaluation Process" by Dr. Jes..."Making the Grade: A Look Inside the Algorithm Evaluation Process" by Dr. Jes...
"Making the Grade: A Look Inside the Algorithm Evaluation Process" by Dr. Jes...
Quantopian
 
"Building Diversified Portfolios that Outperform Out-of-Sample" by Dr. Marcos...
"Building Diversified Portfolios that Outperform Out-of-Sample" by Dr. Marcos..."Building Diversified Portfolios that Outperform Out-of-Sample" by Dr. Marcos...
"Building Diversified Portfolios that Outperform Out-of-Sample" by Dr. Marcos...
Quantopian
 
"From Insufficient Economic data to Economic Big Data – How Trade Data is red...
"From Insufficient Economic data to Economic Big Data – How Trade Data is red..."From Insufficient Economic data to Economic Big Data – How Trade Data is red...
"From Insufficient Economic data to Economic Big Data – How Trade Data is red...
Quantopian
 
"Machine Learning Approaches to Regime-aware Portfolio Management" by Michael...
"Machine Learning Approaches to Regime-aware Portfolio Management" by Michael..."Machine Learning Approaches to Regime-aware Portfolio Management" by Michael...
"Machine Learning Approaches to Regime-aware Portfolio Management" by Michael...
Quantopian
 
"Don't Lose Your Shirt Trading Mean-Reversion" by Edith Mandel, Principal at ...
"Don't Lose Your Shirt Trading Mean-Reversion" by Edith Mandel, Principal at ..."Don't Lose Your Shirt Trading Mean-Reversion" by Edith Mandel, Principal at ...
"Don't Lose Your Shirt Trading Mean-Reversion" by Edith Mandel, Principal at ...
Quantopian
 
"Quantum Hierarchical Risk Parity - A Quantum-Inspired Approach to Portfolio ...
"Quantum Hierarchical Risk Parity - A Quantum-Inspired Approach to Portfolio ..."Quantum Hierarchical Risk Parity - A Quantum-Inspired Approach to Portfolio ...
"Quantum Hierarchical Risk Parity - A Quantum-Inspired Approach to Portfolio ...
Quantopian
 
"Snake Oil, Swamp Land, and Factor-Based Investing" by Gary Antonacci, author...
"Snake Oil, Swamp Land, and Factor-Based Investing" by Gary Antonacci, author..."Snake Oil, Swamp Land, and Factor-Based Investing" by Gary Antonacci, author...
"Snake Oil, Swamp Land, and Factor-Based Investing" by Gary Antonacci, author...
Quantopian
 

More from Quantopian (20)

Being open (source) in the traditionally secretive field of quant finance.
Being open (source) in the traditionally secretive field of quant finance.Being open (source) in the traditionally secretive field of quant finance.
Being open (source) in the traditionally secretive field of quant finance.
 
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
Stauth common pitfalls_stock_market_modeling_pqtc_fall2018
 
Tearsheet feedback webinar 10.10.18
Tearsheet feedback webinar 10.10.18Tearsheet feedback webinar 10.10.18
Tearsheet feedback webinar 10.10.18
 
"Three Dimensional Time: Working with Alternative Data" by Kathryn Glowinski,...
"Three Dimensional Time: Working with Alternative Data" by Kathryn Glowinski,..."Three Dimensional Time: Working with Alternative Data" by Kathryn Glowinski,...
"Three Dimensional Time: Working with Alternative Data" by Kathryn Glowinski,...
 
"Alpha from Alternative Data" by Emmett Kilduff, Founder and CEO of Eagle Alpha
"Alpha from Alternative Data" by Emmett Kilduff,  Founder and CEO of Eagle Alpha"Alpha from Alternative Data" by Emmett Kilduff,  Founder and CEO of Eagle Alpha
"Alpha from Alternative Data" by Emmett Kilduff, Founder and CEO of Eagle Alpha
 
"Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese...
"Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese..."Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese...
"Supply Chain Earnings Diffusion" by Josh Holcroft, Head of Quantitative Rese...
 
"Portfolio Optimisation When You Don’t Know the Future (or the Past)" by Rob...
"Portfolio Optimisation When You Don’t Know the Future (or the Past)" by Rob..."Portfolio Optimisation When You Don’t Know the Future (or the Past)" by Rob...
"Portfolio Optimisation When You Don’t Know the Future (or the Past)" by Rob...
 
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...
“Real Time Machine Learning Architecture and Sentiment Analysis Applied to Fi...
 
“Market Insights Through the Lens of a Risk Model” by Olivier d'Assier, Head ...
“Market Insights Through the Lens of a Risk Model” by Olivier d'Assier, Head ...“Market Insights Through the Lens of a Risk Model” by Olivier d'Assier, Head ...
“Market Insights Through the Lens of a Risk Model” by Olivier d'Assier, Head ...
 
"Maximize Alpha with Systematic Factor Testing" by Cheng Peng, Software Engin...
"Maximize Alpha with Systematic Factor Testing" by Cheng Peng, Software Engin..."Maximize Alpha with Systematic Factor Testing" by Cheng Peng, Software Engin...
"Maximize Alpha with Systematic Factor Testing" by Cheng Peng, Software Engin...
 
"How to Run a Quantitative Trading Business in China with Python" by Xiaoyou ...
"How to Run a Quantitative Trading Business in China with Python" by Xiaoyou ..."How to Run a Quantitative Trading Business in China with Python" by Xiaoyou ...
"How to Run a Quantitative Trading Business in China with Python" by Xiaoyou ...
 
"Fundamental Forecasts: Methods and Timing" by Vinesh Jha, CEO of ExtractAlpha
"Fundamental Forecasts: Methods and Timing" by Vinesh Jha, CEO of ExtractAlpha"Fundamental Forecasts: Methods and Timing" by Vinesh Jha, CEO of ExtractAlpha
"Fundamental Forecasts: Methods and Timing" by Vinesh Jha, CEO of ExtractAlpha
 
"Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Boo...
"Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Boo..."Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Boo...
"Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Boo...
 
"Making the Grade: A Look Inside the Algorithm Evaluation Process" by Dr. Jes...
"Making the Grade: A Look Inside the Algorithm Evaluation Process" by Dr. Jes..."Making the Grade: A Look Inside the Algorithm Evaluation Process" by Dr. Jes...
"Making the Grade: A Look Inside the Algorithm Evaluation Process" by Dr. Jes...
 
"Building Diversified Portfolios that Outperform Out-of-Sample" by Dr. Marcos...
"Building Diversified Portfolios that Outperform Out-of-Sample" by Dr. Marcos..."Building Diversified Portfolios that Outperform Out-of-Sample" by Dr. Marcos...
"Building Diversified Portfolios that Outperform Out-of-Sample" by Dr. Marcos...
 
"From Insufficient Economic data to Economic Big Data – How Trade Data is red...
"From Insufficient Economic data to Economic Big Data – How Trade Data is red..."From Insufficient Economic data to Economic Big Data – How Trade Data is red...
"From Insufficient Economic data to Economic Big Data – How Trade Data is red...
 
"Machine Learning Approaches to Regime-aware Portfolio Management" by Michael...
"Machine Learning Approaches to Regime-aware Portfolio Management" by Michael..."Machine Learning Approaches to Regime-aware Portfolio Management" by Michael...
"Machine Learning Approaches to Regime-aware Portfolio Management" by Michael...
 
"Don't Lose Your Shirt Trading Mean-Reversion" by Edith Mandel, Principal at ...
"Don't Lose Your Shirt Trading Mean-Reversion" by Edith Mandel, Principal at ..."Don't Lose Your Shirt Trading Mean-Reversion" by Edith Mandel, Principal at ...
"Don't Lose Your Shirt Trading Mean-Reversion" by Edith Mandel, Principal at ...
 
"Quantum Hierarchical Risk Parity - A Quantum-Inspired Approach to Portfolio ...
"Quantum Hierarchical Risk Parity - A Quantum-Inspired Approach to Portfolio ..."Quantum Hierarchical Risk Parity - A Quantum-Inspired Approach to Portfolio ...
"Quantum Hierarchical Risk Parity - A Quantum-Inspired Approach to Portfolio ...
 
"Snake Oil, Swamp Land, and Factor-Based Investing" by Gary Antonacci, author...
"Snake Oil, Swamp Land, and Factor-Based Investing" by Gary Antonacci, author..."Snake Oil, Swamp Land, and Factor-Based Investing" by Gary Antonacci, author...
"Snake Oil, Swamp Land, and Factor-Based Investing" by Gary Antonacci, author...
 

Recently uploaded

when will pi network coin be available on crypto exchange.
when will pi network coin be available on crypto exchange.when will pi network coin be available on crypto exchange.
when will pi network coin be available on crypto exchange.
DOT TECH
 
USDA Loans in California: A Comprehensive Overview.pptx
USDA Loans in California: A Comprehensive Overview.pptxUSDA Loans in California: A Comprehensive Overview.pptx
USDA Loans in California: A Comprehensive Overview.pptx
marketing367770
 
PF-Wagner's Theory of Public Expenditure.pptx
PF-Wagner's Theory of Public Expenditure.pptxPF-Wagner's Theory of Public Expenditure.pptx
PF-Wagner's Theory of Public Expenditure.pptx
GunjanSharma28848
 
NO1 Uk Black Magic Specialist Expert In Sahiwal, Okara, Hafizabad, Mandi Bah...
NO1 Uk Black Magic Specialist Expert In Sahiwal, Okara, Hafizabad,  Mandi Bah...NO1 Uk Black Magic Specialist Expert In Sahiwal, Okara, Hafizabad,  Mandi Bah...
NO1 Uk Black Magic Specialist Expert In Sahiwal, Okara, Hafizabad, Mandi Bah...
Amil Baba Dawood bangali
 
how can I sell my pi coins for cash in a pi APP
how can I sell my pi coins for cash in a pi APPhow can I sell my pi coins for cash in a pi APP
how can I sell my pi coins for cash in a pi APP
DOT TECH
 
What website can I sell pi coins securely.
What website can I sell pi coins securely.What website can I sell pi coins securely.
What website can I sell pi coins securely.
DOT TECH
 
Webinar Exploring DORA for Fintechs - Simont Braun
Webinar Exploring DORA for Fintechs - Simont BraunWebinar Exploring DORA for Fintechs - Simont Braun
Webinar Exploring DORA for Fintechs - Simont Braun
FinTech Belgium
 
What price will pi network be listed on exchanges
What price will pi network be listed on exchangesWhat price will pi network be listed on exchanges
What price will pi network be listed on exchanges
DOT TECH
 
how to sell pi coins effectively (from 50 - 100k pi)
how to sell pi coins effectively (from 50 - 100k  pi)how to sell pi coins effectively (from 50 - 100k  pi)
how to sell pi coins effectively (from 50 - 100k pi)
DOT TECH
 
what is the best method to sell pi coins in 2024
what is the best method to sell pi coins in 2024what is the best method to sell pi coins in 2024
what is the best method to sell pi coins in 2024
DOT TECH
 
Poonawalla Fincorp and IndusInd Bank Introduce New Co-Branded Credit Card
Poonawalla Fincorp and IndusInd Bank Introduce New Co-Branded Credit CardPoonawalla Fincorp and IndusInd Bank Introduce New Co-Branded Credit Card
Poonawalla Fincorp and IndusInd Bank Introduce New Co-Branded Credit Card
nickysharmasucks
 
Introduction to Indian Financial System ()
Introduction to Indian Financial System ()Introduction to Indian Financial System ()
Introduction to Indian Financial System ()
Avanish Goel
 
how to sell pi coins in South Korea profitably.
how to sell pi coins in South Korea profitably.how to sell pi coins in South Korea profitably.
how to sell pi coins in South Korea profitably.
DOT TECH
 
一比一原版Birmingham毕业证伯明翰大学|学院毕业证成绩单如何办理
一比一原版Birmingham毕业证伯明翰大学|学院毕业证成绩单如何办理一比一原版Birmingham毕业证伯明翰大学|学院毕业证成绩单如何办理
一比一原版Birmingham毕业证伯明翰大学|学院毕业证成绩单如何办理
betoozp
 
US Economic Outlook - Being Decided - M Capital Group August 2021.pdf
US Economic Outlook - Being Decided - M Capital Group August 2021.pdfUS Economic Outlook - Being Decided - M Capital Group August 2021.pdf
US Economic Outlook - Being Decided - M Capital Group August 2021.pdf
pchutichetpong
 
Economics and Economic reasoning Chap. 1
Economics and Economic reasoning Chap. 1Economics and Economic reasoning Chap. 1
Economics and Economic reasoning Chap. 1
Fitri Safira
 
Turin Startup Ecosystem 2024 - Ricerca sulle Startup e il Sistema dell'Innov...
Turin Startup Ecosystem 2024  - Ricerca sulle Startup e il Sistema dell'Innov...Turin Startup Ecosystem 2024  - Ricerca sulle Startup e il Sistema dell'Innov...
Turin Startup Ecosystem 2024 - Ricerca sulle Startup e il Sistema dell'Innov...
Quotidiano Piemontese
 
how to sell pi coins on Binance exchange
how to sell pi coins on Binance exchangehow to sell pi coins on Binance exchange
how to sell pi coins on Binance exchange
DOT TECH
 
The European Unemployment Puzzle: implications from population aging
The European Unemployment Puzzle: implications from population agingThe European Unemployment Puzzle: implications from population aging
The European Unemployment Puzzle: implications from population aging
GRAPE
 
一比一原版BCU毕业证伯明翰城市大学毕业证成绩单如何办理
一比一原版BCU毕业证伯明翰城市大学毕业证成绩单如何办理一比一原版BCU毕业证伯明翰城市大学毕业证成绩单如何办理
一比一原版BCU毕业证伯明翰城市大学毕业证成绩单如何办理
ydubwyt
 

Recently uploaded (20)

when will pi network coin be available on crypto exchange.
when will pi network coin be available on crypto exchange.when will pi network coin be available on crypto exchange.
when will pi network coin be available on crypto exchange.
 
USDA Loans in California: A Comprehensive Overview.pptx
USDA Loans in California: A Comprehensive Overview.pptxUSDA Loans in California: A Comprehensive Overview.pptx
USDA Loans in California: A Comprehensive Overview.pptx
 
PF-Wagner's Theory of Public Expenditure.pptx
PF-Wagner's Theory of Public Expenditure.pptxPF-Wagner's Theory of Public Expenditure.pptx
PF-Wagner's Theory of Public Expenditure.pptx
 
NO1 Uk Black Magic Specialist Expert In Sahiwal, Okara, Hafizabad, Mandi Bah...
NO1 Uk Black Magic Specialist Expert In Sahiwal, Okara, Hafizabad,  Mandi Bah...NO1 Uk Black Magic Specialist Expert In Sahiwal, Okara, Hafizabad,  Mandi Bah...
NO1 Uk Black Magic Specialist Expert In Sahiwal, Okara, Hafizabad, Mandi Bah...
 
how can I sell my pi coins for cash in a pi APP
how can I sell my pi coins for cash in a pi APPhow can I sell my pi coins for cash in a pi APP
how can I sell my pi coins for cash in a pi APP
 
What website can I sell pi coins securely.
What website can I sell pi coins securely.What website can I sell pi coins securely.
What website can I sell pi coins securely.
 
Webinar Exploring DORA for Fintechs - Simont Braun
Webinar Exploring DORA for Fintechs - Simont BraunWebinar Exploring DORA for Fintechs - Simont Braun
Webinar Exploring DORA for Fintechs - Simont Braun
 
What price will pi network be listed on exchanges
What price will pi network be listed on exchangesWhat price will pi network be listed on exchanges
What price will pi network be listed on exchanges
 
how to sell pi coins effectively (from 50 - 100k pi)
how to sell pi coins effectively (from 50 - 100k  pi)how to sell pi coins effectively (from 50 - 100k  pi)
how to sell pi coins effectively (from 50 - 100k pi)
 
what is the best method to sell pi coins in 2024
what is the best method to sell pi coins in 2024what is the best method to sell pi coins in 2024
what is the best method to sell pi coins in 2024
 
Poonawalla Fincorp and IndusInd Bank Introduce New Co-Branded Credit Card
Poonawalla Fincorp and IndusInd Bank Introduce New Co-Branded Credit CardPoonawalla Fincorp and IndusInd Bank Introduce New Co-Branded Credit Card
Poonawalla Fincorp and IndusInd Bank Introduce New Co-Branded Credit Card
 
Introduction to Indian Financial System ()
Introduction to Indian Financial System ()Introduction to Indian Financial System ()
Introduction to Indian Financial System ()
 
how to sell pi coins in South Korea profitably.
how to sell pi coins in South Korea profitably.how to sell pi coins in South Korea profitably.
how to sell pi coins in South Korea profitably.
 
一比一原版Birmingham毕业证伯明翰大学|学院毕业证成绩单如何办理
一比一原版Birmingham毕业证伯明翰大学|学院毕业证成绩单如何办理一比一原版Birmingham毕业证伯明翰大学|学院毕业证成绩单如何办理
一比一原版Birmingham毕业证伯明翰大学|学院毕业证成绩单如何办理
 
US Economic Outlook - Being Decided - M Capital Group August 2021.pdf
US Economic Outlook - Being Decided - M Capital Group August 2021.pdfUS Economic Outlook - Being Decided - M Capital Group August 2021.pdf
US Economic Outlook - Being Decided - M Capital Group August 2021.pdf
 
Economics and Economic reasoning Chap. 1
Economics and Economic reasoning Chap. 1Economics and Economic reasoning Chap. 1
Economics and Economic reasoning Chap. 1
 
Turin Startup Ecosystem 2024 - Ricerca sulle Startup e il Sistema dell'Innov...
Turin Startup Ecosystem 2024  - Ricerca sulle Startup e il Sistema dell'Innov...Turin Startup Ecosystem 2024  - Ricerca sulle Startup e il Sistema dell'Innov...
Turin Startup Ecosystem 2024 - Ricerca sulle Startup e il Sistema dell'Innov...
 
how to sell pi coins on Binance exchange
how to sell pi coins on Binance exchangehow to sell pi coins on Binance exchange
how to sell pi coins on Binance exchange
 
The European Unemployment Puzzle: implications from population aging
The European Unemployment Puzzle: implications from population agingThe European Unemployment Puzzle: implications from population aging
The European Unemployment Puzzle: implications from population aging
 
一比一原版BCU毕业证伯明翰城市大学毕业证成绩单如何办理
一比一原版BCU毕业证伯明翰城市大学毕业证成绩单如何办理一比一原版BCU毕业证伯明翰城市大学毕业证成绩单如何办理
一比一原版BCU毕业证伯明翰城市大学毕业证成绩单如何办理
 

From Backtesting to Live Trading by Vesna Straser at QuantCon 2016

  • 1. From Back Testing to Live Trading Vesna Straser, PhD QuantCon, April 2016
  • 2. Trade System Design Process Trade Model and System Design •Evaluate signal strength & expected alpha •Check for model overfitting •Check for look ahead biases •Optimize system parameters Back Testing •Conduct out- of- sample testing •Check for data consistency •Evaluate system risk parameters •Evaluate position liquidity •Use simplified order fill and TC models Simulation / Paper Trading •Trade a strategy using tick data at simulated prices, trade cost, and fill rates •Use market simulator that mirrors strategy type Live Trading •Commit capital to trade with real market data at actual prices, fill rates, and trade costs Execution Testing Phase Model Testing Phase
  • 3. Performance Delta Between Back Test, Simulation, and Live Trading  Two sets of factors:  Trade model / system specific → what and how much to trade  Bad data, over-fitted model, poor out of sample performance  Depends on signal research and modeling nuances  Trade execution specific → how to trade  Related to order fill assumptions: how orders are filled in terms of price, size, and time  Can be responsible for large discrepancies in trading performance  High turnover strategies will tend to have greater discrepancies
  • 4. Execution Factors Driving Performance Delta Back Testing Simulation Trading Live Trading Data Structure OHLCV bar values built from trade data Bar or Tick Data Market Depth Level I Tick Data Market Depth Signal Calculation End of bar EOB or on every tick On every tick Fill Price = f (order type) Fixed (OHLC) Simulated Market Driven Fill Rate = f (order type) 100% Simulated ≤ 100% Market Driven ≤ 100% Transaction Cost = f (order type) Fixed TC Model Market Driven Trade Count = f (system settings) One trade per bar One or Market Driven Market Driven Latency Not included Network Network and Exchange Strategy type and holding time
  • 5. Example: One System, Two P&Ls  Mean Reversion System using 10 minutes time interval  Back Test stats: o P&L: $188.5 o 6 trades  Simulation stats: o P&L: $112.5 o 5 trades Trade did not occur in Simulation because entry signal was not true in real time Sim Trade exited at different time due to real time price dynamics Sim Trade entry price is higher (worse) than Back Test Price
  • 6. Comparing Price Slippage Actual Trade. Price Decision Price Simulation Trade Price Slippage Signal = True Decision Time Price TimeNext Bar Open BT Price Open BT Price Close Next Bar Close Bar 33 Bar 34 Bar 35 Bar 36 Bar 37
  • 7. Comparing P&L Slippage Next Open Entry Time Time Next Close Next Open Next Close BT EnOP BT EnCP AEnP ST EnP Entry = True Price D EnP BT ExOP O P&L ST ExP S P&L BT ExCP C P&L Exit Time Exit = True D ExP D P&L Bar 33 Bar 34 Bar 35 Bar 36 Bar 37 AExP A P&L Timing Risk
  • 8. Comparing Trade Count DynamicsPrice Time S P&L Bar 33 Bar 34 Bar 35 Bar 36 Bar 37 A P&L O P&L C P&L Exit = True Trade 1 BT Trade 1 Entry = True Exit = True D P%L Entry = True Trade 2
  • 9. Understanding Back Testing Limitations  Signal is evaluated at the end of bar not intra-bar on every tick → lower/higher trade count  Actual price movement within a bar is not known → which order gets filled first?  Only one trade (entry or exit) per bar possible → lower trade count  MO are filled at OC prices (user specified) → slippage  LO are filled if limit price is within the HL range → 100% fill rate  In case of multiple active limit orders BT engine may fill all limit orders → overfills?  Inability to account for sudden price moves / gaps → higher fill rate or trade count  Simplified fill model: based on trade prices only (vs bid/ask data) → lower spread cost  100% fill rate if missing volume data → higher fill rate and lower market impact  Slippage is incorporated as fixed rate (in ticks / cents) → imprecise market impact  Missing network latency → higher fill rate and trade count
  • 10. Improving Back Testing Accuracy  Incorporate intra-bar price movement assumptions:  If O is closer to H, assume O – H – L – C price move  If O is closer to L or in the middle assume O – L – H – C  Know which limit order gets filled first, “cancel” others  Hybrid OHLC and tick data approach: add tick data replay for bars where signal is true  Incorporate bid/ask data or spread to achieve more realistic fill price and spread cost  Buy market orders are filled at ask prices  Sell market orders are filled at bid prices  Trade price closest to the decision time (e.g., O) would generate more accurate slippage  If configurable, assume conservative fill model for limit orders (limit price vs HL)  Incorporate Volume data to fine tune fill rate and market impact assumptions:  Limit fill size to % of bar volume allowing for partial fills  Make market impact model a function of relative order size: order size / bar volume
  • 11. Understanding Simulation Trading Limitations  Signals are processed using OHLC or tick data (replayed or in real time) → Is the signal processing timing in sync with BT?  Orders are processed using tick data but are filled per various order fill assumptions applied in market simulator  Not all market simulators use level 2 data in simulating order fills (Interactive Brokers is using level 1 only)  Order fill probability (price and size at which order is filled) is function of many dynamic variables:  Order type: market, limit, stop, pegged  Order size  Bid/Ask volume = visible + hidden  Market depth = visible + hidden  Trade volume  Time of day  Place in queue = f (number of limit orders in the queue)  Executing/routing exchange = f (liquidity, order processing latency, market conditions)  Latency = f (network, broker, exchange, market conditions) → may cause missed trades in live trading  Market conditions = f(volatility, trade rate, momentum, price gaps) → may cause missed trades in live trading  Impact of limit orders on market depth changes is difficult to capture
  • 12. Improving Simulation Trading Accuracy  Use realistic limit order fill assumptions, e.g., limit order is filled when trade price:  touches a limit price → most liberal  trades through the limit price  trades through the limit price by X ticks → conservative  touches the limit price X times, where X = f (place in queue) → most realistic  fill price = Limit price → conservative  fill price = Trade Price → liberal, assumes price improvement  Market depth significantly improves accuracy of market order fill prices in case of partial fills  Use bid/ask volume for a more realistic market order fill rate  account for partial fills when order size > bid/ask size  Use customizable transaction cost model = f (order size, side, spread, volume, depth, volatility, horizon)  Use dynamic latency model = f (real time network latency, avg exchange latency, avg order processing latency)
  • 13. Defining Strategy Holding Time milliseconds seconds minutes hours days weeks HIGH FREQUENCY  HT = milliseconds to seconds  Expected Profit < 1 spread  Order size = very small  Cost sensitivity: very high  Trading concern = speed  Strategy types:  Latency arbitrage  Statistical arbitrage  Market making  Pairs/spread trading INTRA DAY  HT = minutes to hours  Expected profit = x * spread  Order size = small  Cost sensitivity: high  Trading concern = spread capture  Strategy types:  TA pattern following  Momentum/Reversal  Scalping  News LOW FREQUENCY  HT = days to months  Expected profit > 1%  Order size = larger  Cost sensitivity: moderate  Trading concern = liquidity  Strategy types:  Long / Short  Fundamental Factors  Earnings quality
  • 14. Back Testing and Simulation Model Selection HFT INTRA DAY LOW FREQUENCY  Back Testing = Simulation Model  Use level 2 data  Need custom built simulator; off the shelf products do not capture sufficient details  Custom TC model = f (trade strategy)  Latency is critical  Use O B/A based prices to fill market orders  Apply intra-bar price move assumptions  Use bar volume data  Apply spread based TC model  Use level 2 data  Use conservative limit order fill model  Apply small order TC model  Account for latency  Level 1 is sufficient, level 2 is better  Apply order size limits  Use complex order types (e.g., VWAP)  Apply large (parent) order TC model  Use conservative prices to fill orders, e.g., (H+L)/2, VWAP (if orders are large)  Use bar volume data to limit order size or estimate execution horizon  Apply conservative TC assumptions BACK TEST SIMULATION
  • 15. Takeaways 1. Pick BT and ST provider that supports highest level of customizability for your trading style 2. Know the nuances of the BT and ST platforms you are using 3. Pick data structure, fill model, and other settings that most closely match your trading strategy 4. Assure consistency of data, order processing, and fill model assumptions between BT and ST platforms vis a vis live trading 5. Use level 2 tick data in ST 6. Strategies with longer trading horizons and higher expected alpha will have more accurate BT and ST results vis a vis live trading 7. Understand the specifics of the market structure of the products you are trading (stocks vs futures vs FX vs options) 8. Stick to low turnover strategies, liquid trading universe, small order sizes, and be conservative