QuantInsti was invited to Participate in SGX India Suite in AFACT (Association of Financial and Commodity Traders, Singapore).
Mr. Nitesh Khandelwal, Founder of QuantInsti, spoke at SGX-India chapter in AFACT in Singapore on the 23rd of May. He gave a detailed presentation covering various Quantitative Trading Strategies. The session was based on the real life quantitative trading strategies with actual market data. Various models were also shown and explained to the audience.The presentation was very well received by the participants, which included many members of Association of Financial and Commodity Traders, Singapore.
Tap into the macro-economic coverage on India and gain trading insights centered around SGX’s India suite of derivative products namely SGX CNX Nifty Index Futures, SGX MSCI India Index Futures, SGX INR/USD FX Futures. With speakers covering macro-economic developments and delving into the finer details of trading strategies, this was an event not to be missed.
You can find a detailed version of this presentation on our blog - http://www.quantinsti.com/blog/afact-time-for-sgx-sgx-india-suite/
Connect with us:
Facebook - http://facebook.com/quantinsti
Twitter - http://twitter.com/quantinsti
Youtube - http://youtube.com/quantinsti
3. 3
Quantitative Trading
• Using quantitative techniques to build the trading
model and execution. Statistical methods and
mathematical computations are extensively used while
creating the trading model as well as the during the
implementation.
Definitions Statistics Strategies Stat Arb
Quantitative Trading
• Using quantitative techniques to build the trading
model and execution. Statistical methods and
mathematical computations are extensively used while
creating the trading model as well as the during the
implementation.
4. 4
Statistical Concepts
• Stationarity
• Cointegration
• Dickey Fuller test
Definitions Statistics Strategies Stat Arb
Statistical Concepts
• Stationarity
• Cointegration
• Dickey Fuller test
5. 5
Statistical Concepts: Stationarity
• A stationary time series is one whose statistical properties such as mean,
variance, autocorrelation, etc. are all constant over time. Most statistical
forecasting methods are based on the assumption that the time series can
be rendered approximately stationary (i.e., "stationarized") through the use
of mathematical transformations.
• A stationarized series is relatively easy to predict: you simply predict that its
statistical properties will be the same in the future as they have been in the
past! The predictions for the stationarized series can then be
"untransformed," by reversing whatever mathematical transformations were
previously used, to obtain predictions for the original series.
Definitions Statistics Strategies Stat Arb
Statistical Concepts: Stationarity
• A stationary time series is one whose statistical properties such as mean,
variance, autocorrelation, etc. are all constant over time. Most statistical
forecasting methods are based on the assumption that the time series can
be rendered approximately stationary (i.e., "stationarized") through the use
of mathematical transformations.
• A stationarized series is relatively easy to predict: you simply predict that its
statistical properties will be the same in the future as they have been in the
past! The predictions for the stationarized series can then be
"untransformed," by reversing whatever mathematical transformations were
previously used, to obtain predictions for the original series.
6. 6
Statistical Concepts: Cointegration
• Two time series are cointegrated if they have a common
stochastic drift*. Typically you can determine this by checking if:
For two individually non stationary time series, there exists a
linear combination of the two time series that is stationary.
Example: Walking man and his dog.
Definitions Statistics Strategies Stat Arb
*Stochastic Drift: Change of the average value of a stochastic process. Example: Stock prices
7. 7
Statistical Concepts: DF Test
It test for the unit root in an autoregressive model.
yt = ρ yt-1 + ut
If |ρ| >= 1, then a unit root is present and the series is non
stationary
Definitions Statistics Strategies Stat Arb
Statistical Concepts: DF Test
It test for the unit root in an autoregressive model.
yt = ρ yt-1 + ut
If |ρ| >= 1, then a unit root is present and the series is non
stationary
8. 8
ETF/Cash - Future Arbitrage:
• Long Cash (or ETF)/ Short Future
• Short Cash (or ETF)/ Long Future
• Strategy Notes:
– When shorting Cash/ETF, ensure its allowed for Short
selling
– Pick stocks with liquid cash market
– Spreads become more volatile when close to expiry
– Higher interest rates typically indicate higher spreads
– Market Sentiment
Futures Trading Strategies
Cash Future
Stat Arbitrage
Definitions Statistics Strategies Stat Arb
ETF/Cash - Future Arbitrage:
• Long Cash (or ETF)/ Short Future
• Short Cash (or ETF)/ Long Future
• Strategy Notes:
– When shorting Cash/ETF, ensure its allowed for Short
selling
– Pick stocks with liquid cash market
– Spreads become more volatile when close to expiry
– Higher interest rates typically indicate higher spreads
– Market Sentiment
Index Arbitrage
Directional
9. 9
Calendar Spreads:
• INR May 2015 Vs INR June 2015
Inter Product Spreads:
• SGX Nifty Vs SGX MSCI India Futures
• SGX Nifty Vs SGX INR Futures
Inter Destinations Spreads:
• SGX INR Vs INR NDF
• SGX JPY Vs Spot JPY
Futures Trading Strategies
Cash Future
Stat Arbitrage
Definitions Statistics Strategies Stat Arb
Calendar Spreads:
• INR May 2015 Vs INR June 2015
Inter Product Spreads:
• SGX Nifty Vs SGX MSCI India Futures
• SGX Nifty Vs SGX INR Futures
Inter Destinations Spreads:
• SGX INR Vs INR NDF
• SGX JPY Vs Spot JPY
Index Arbitrage
Directional
10. 10
Futures Trading Strategies
SGX NIFTY MSCI India Future Strategy notes
Product 50 stocks 64 stocks Highly correlated pair (99%
correlation)
Lot size 2 times the index 50 times the index MSCI contract size is approx 3.1
times the Nifty contract
Tick Size 0.5 index points (USD 1) 0.2 index points (USD 10) Correct rounding
Daily Price Range 10/15/20% 10/15/20% Same ‘mostly’
Definitions Statistics Strategies Stat Arb
Contract Months 2 nearest months and 4
quarterly months
2 nearest months and 4
months on yearly cycle
Near month is most liquid
Trading Hours 9am to 6:10pm, 7:15pm
to 2am
9am to 6:10pm, 7:15pm to
2am
Same
Last Trading Day Last Thursday of the
month
Last Thursday of the
month
They expire at their respective
index values
Settlement Cash Cash Same
12. 12
Correlation
• 99% correlation
– More importantly, they are cointegrated!
Spread Margin Benefit
• 70% margin credit for 3 lots of Nifty against
1 lot of MSCI India Future
Nifty Vs MSCI Futures
Cash Future
Stat Arbitrage
Definitions Statistics Strategies Stat Arb
Correlation
• 99% correlation
– More importantly, they are cointegrated!
Spread Margin Benefit
• 70% margin credit for 3 lots of Nifty against
1 lot of MSCI India Future
Index Arbitrage
Directional
13. 13
Futures Trading Strategies
Cash Future
Stat Arbitrage
Index Arbitrage:
• Long Nifty Future/ Short Constituent
Stocks/Futures
• Short Nifty Future/ Long Constituent
Stocks/Futures
• Strategy Notes:
– When shorting Cash, ensure its allowed for Short selling
– Approximate Index replication
– Trade Size
– Transaction Cost
– Index Future with Cash Stock + Stock Future
Definitions Statistics Strategies Stat Arb
Index Arbitrage
Directional
Index Arbitrage:
• Long Nifty Future/ Short Constituent
Stocks/Futures
• Short Nifty Future/ Long Constituent
Stocks/Futures
• Strategy Notes:
– When shorting Cash, ensure its allowed for Short selling
– Approximate Index replication
– Trade Size
– Transaction Cost
– Index Future with Cash Stock + Stock Future
14. 14
Futures Trading Strategies
Cash Future
Stat Arbitrage
Directional Trading Strategies:
• Trading Strategies based on indicators/quantitative analysis
Strategy
Ideation
Definitions Statistics Strategies Stat Arb
Index Arbitrage
Directional
Directional Trading Strategies:
• Trading Strategies based on indicators/quantitative analysis
Strategy
Modeling
Back Testing
Parameter
Optimization
Implementation
Risk
Management
15. 15
Ideation & Validation
• Check for cointegration
Modeling
• Create a mean reverting index and model the strategy
– Key inputs: Signal generation parameters, SL, TP, Order quantity
Back-testing
• Calculate the key outputs
– Net profit, average profit, drawdown, returns, ratios
Implementation
• Causality & exceptions
Stat Arb Example: Strategy Building Process
Definitions Statistics Strategies Stat Arb
Ideation & Validation
• Check for cointegration
Modeling
• Create a mean reverting index and model the strategy
– Key inputs: Signal generation parameters, SL, TP, Order quantity
Back-testing
• Calculate the key outputs
– Net profit, average profit, drawdown, returns, ratios
Implementation
• Causality & exceptions
16. 16
Nifty Vs MSCI
• Trade Idea: Given overlap of constituents in MSCI India
Index and Nifty Index, some cointegration can be sensed.
Idea is to buy Nifty Future, sell MSCI India Future and
vice versa as per the signal with similar notional
• Test for cointegration and generate signals based on z-
score
• Trade Nifty Futures against MSCI Futures in 3:1 ratio
• Two-leg strategy, i.e. orders sent in both the legs
• Stop Loss & Take Profit based trade exits
• Market Risk: Low
Strategy 1: Statistical Arbitrage
Definitions Statistics Strategies Stat Arb
Nifty Vs MSCI
• Trade Idea: Given overlap of constituents in MSCI India
Index and Nifty Index, some cointegration can be sensed.
Idea is to buy Nifty Future, sell MSCI India Future and
vice versa as per the signal with similar notional
• Test for cointegration and generate signals based on z-
score
• Trade Nifty Futures against MSCI Futures in 3:1 ratio
• Two-leg strategy, i.e. orders sent in both the legs
• Stop Loss & Take Profit based trade exits
• Market Risk: Low
17. 17
MSCI ETF Vs MSCI Future
• Trade Idea: ETF assumed as the lead indicator (ideally to
be tested through Granger Causality or other Causality
models). If the ETF returns are exceeding Future’s
return, take a short term naked position in MSCI Future.
• Trade MSCI Futures based on ETF Returns
• Single leg strategy, i.e. orders sent only in MSCI Futues
but ETF data used as well.
• Trade exit: When signal on the opposite side is
generated
• Market Risk: Medium
Strategy 2: Trading Causality
Definitions Statistics Strategies Stat Arb
MSCI ETF Vs MSCI Future
• Trade Idea: ETF assumed as the lead indicator (ideally to
be tested through Granger Causality or other Causality
models). If the ETF returns are exceeding Future’s
return, take a short term naked position in MSCI Future.
• Trade MSCI Futures based on ETF Returns
• Single leg strategy, i.e. orders sent only in MSCI Futues
but ETF data used as well.
• Trade exit: When signal on the opposite side is
generated
• Market Risk: Medium
18. 18
INR Futures
• Trade Idea: To ride on the short term trend of the INR
futures with exits based on Stop Loss and Take Profit.
• Trend Following model
• Trading signal generated when current closing price goes
above or below (buy or sell respectively) max/min of
previous ‘x’ days closing price
• Single leg strategy, i.e. orders sent only in INR Futures
• Trade exit: When Stop Loss or Take Profit is triggered.
• Market Risk: High
Strategy 3: Trend Following Strategy
Definitions Statistics Strategies Stat Arb
INR Futures
• Trade Idea: To ride on the short term trend of the INR
futures with exits based on Stop Loss and Take Profit.
• Trend Following model
• Trading signal generated when current closing price goes
above or below (buy or sell respectively) max/min of
previous ‘x’ days closing price
• Single leg strategy, i.e. orders sent only in INR Futures
• Trade exit: When Stop Loss or Take Profit is triggered.
• Market Risk: High
21. 21
Definitions
• Financial Derivative is a financial instrument whose price is
derived from the price of some other financial instrument.
• Futures & Forwards:
– Future: Standardized contracts for the purchase and sale of financial
instruments or physical commodities for future delivery on a regulated
exchange.
– Forward: A private over the counter (OTC) agreement between a
buyer and seller for the future delivery of a commodity or a financial
instrument, at an agreed upon price. In contrast to futures
contracts, forward contracts are not standardized and are non-
transferable.
Definitions Fundaments Pricing
Definitions
• Financial Derivative is a financial instrument whose price is
derived from the price of some other financial instrument.
• Futures & Forwards:
– Future: Standardized contracts for the purchase and sale of financial
instruments or physical commodities for future delivery on a regulated
exchange.
– Forward: A private over the counter (OTC) agreement between a
buyer and seller for the future delivery of a commodity or a financial
instrument, at an agreed upon price. In contrast to futures
contracts, forward contracts are not standardized and are non-
transferable.
22. 22
Futures
• Financial Derivative is a financial instrument whose price is
derived from the price of some other financial instrument.
• Futures & Forwards:
– Future: Standardized contracts for the purchase and sale of financial
instruments or physical commodities for future delivery on a regulated
exchange.
– Forward: A private over the counter (OTC) agreement between a
buyer and seller for the future delivery of a commodity or a financial
instrument, at an agreed upon price. In contrast to futures
contracts, forward contracts are not standardized and are non-
transferable.
Definitions Fundaments Pricing
Futures
• Financial Derivative is a financial instrument whose price is
derived from the price of some other financial instrument.
• Futures & Forwards:
– Future: Standardized contracts for the purchase and sale of financial
instruments or physical commodities for future delivery on a regulated
exchange.
– Forward: A private over the counter (OTC) agreement between a
buyer and seller for the future delivery of a commodity or a financial
instrument, at an agreed upon price. In contrast to futures
contracts, forward contracts are not standardized and are non-
transferable.
23. 23
Market Participants
• Hedgers: Use futures to manage the price risk
• Arbitrageurs: Profit from pricing mismatch
• Speculators: Take price risk to generate profits
Definitions Fundaments Pricing
25. 25
Benefits of Trading Futures
• Capital efficiency: Higher leverage
• More strategies: Different instrument from Cash
• Better liquidity: Bigger notional values
• Price Discovery: Fair and Transparent Price Discovery
Definitions Fundaments Pricing
Benefits of Trading Futures
• Capital efficiency: Higher leverage
• More strategies: Different instrument from Cash
• Better liquidity: Bigger notional values
• Price Discovery: Fair and Transparent Price Discovery
26. 26
Futures Pricing
• Pricing depends on key characteristics of instrument
– Spot Price
– Date of Expiry
– Risk free rate of return
– Storage & Delivery Cost
– Convenience Yield
Definitions Fundaments Pricing
Futures Pricing
• Pricing depends on key characteristics of instrument
– Spot Price
– Date of Expiry
– Risk free rate of return
– Storage & Delivery Cost
– Convenience Yield
27. 27
Futures Pricing: The Math
• For Equity Futures:
F(t, T) = S(t)*er(T-t)
where:
– F (t, T) = Price of the future at time t with expiry on time T
– S(t) = Spot Price at time T
– r = Risk free rate of return
– T = Expiry date
– t = Current date
Definitions Fundaments Pricing
Futures Pricing: The Math
• For Equity Futures:
F(t, T) = S(t)*er(T-t)
where:
– F (t, T) = Price of the future at time t with expiry on time T
– S(t) = Spot Price at time T
– r = Risk free rate of return
– T = Expiry date
– t = Current date
28. 28
Futures Pricing: The Math
• For Commodity Futures:
F(t, T) = S(t)*e(r+s-c)(T-t)
where:
– F = Price of the future
– S = Spot Price
– R = Risk free rate of return
– T = Expiry date
– t = Current date
– s = Storage cost
– c = Convenience Yield
Definitions Fundaments Pricing
Futures Pricing: The Math
• For Commodity Futures:
F(t, T) = S(t)*e(r+s-c)(T-t)
where:
– F = Price of the future
– S = Spot Price
– R = Risk free rate of return
– T = Expiry date
– t = Current date
– s = Storage cost
– c = Convenience Yield
29. 29
Executive Programme in Algorithmic
Trading (E-PAT)
Executive Programme in Algorithmic
Trading (E-PAT)