SlideShare a Scribd company logo
Learnings from 	

Forecasting - Principles and Practice
www.otexts.org/fpp
Basic Modeling
Intro & 	

simple theory
Forecasting
Forecast+Model
www.otexts.org/fpp
Code at:	

https://github.com/thiakx/Forecasting_DSSG
Adapted from the Forecasting: Principles and Practice book
Judgmental Forecasts Machine Generated Forecasts
Judgmental Forecasts
The Basics
Judgmental Forecasts - Principles
Set the forecasting task 	

clearly and concisely
Implement a systematic approach:	

-Document and justify	

-Systematically evaluate forecasts
Segregate forecasters and users
Judgmental Forecasts - How to
Delphi Method - 	

Panel of experts
Ask the executives, staff, 	

customers
Use a proxy 	

(similar cases, best / worst case)
Nate Silver
Machine Generated Forecasts
The Basics
The Basics -Time Series Decomposition
12 month	

seasonal	

trend
The Basics - Seasonality
The Basics - Seasonality +Trend
The Basics - Remainder / Random Error
The Basics - Seasonal sub-series plot
The Basics
The Basics -Time Series Decomposition
then re-seasonalize with thisTrain model with this
The Basics -Time Series Decomposition
then re-seasonalize with thisTrain model with this
The Basics -Time Series Decomposition
95% confidence
80% confidence
then re-seasonalize with thisTrain model with this
The Basics -Time Series Decomposition
then re-seasonalize with thisTrain model with this
Seasonal andTrend decomposition using Loess (STL) code
Córdoba
Using seasonal-trend decomposition based on loess (STL) to	

explore temporal patterns of pneumonic lesions in finishing	

pigs slaughtered in England, 2005–2011
Córdoba
Using seasonal-trend decomposition based on loess (STL) to	

explore temporal patterns of pneumonic lesions in finishing	

pigs slaughtered in England, 2005–2011
STL is suitable as the overall trend fluctuates a fair bit
Machine Generated Forecasts
Time Series Forecasting:	

Exponential smoothing
Time Series Forecasts - Holts-Winters
Time Series Forecasts - Exponential Smoothing
Time Series Forecasts - Exponential Smoothing
More relevantLess relevant
Something to represent fall in relevance?
Time Series Forecasts - Exponential Smoothing
Smoothing Parameter α = 0.8
0.8
0.16
0.032
0.064
T1
T2
T3
T4
T1-T4
Time Series Forecasts - Exponential Smoothing
T1-T4
Smoothing Parameter α = decided by minimizing error rate
Time Series Forecasts - Damping
Undamped projection
Damped projection
Time Series Forecasts - Additive vs Multiplicative
The additive method is
preferred when the
seasonal variations are
roughly constant
through the series,
while the multiplicative
method is preferred
when the seasonal
variations are changing
proportional to the
level of the series.
Time Series Forecasts - Holts-Winters
Link to: Usage of Modified Holt-Winters Method in the 	

Anomaly Detection of NetworkTraffic: Case Studies
Link to: Usage of Modified Holt-Winters Method in the 	

Anomaly Detection of NetworkTraffic: Case Studies
Holt-Winter is suitable as the most recent behavior that deviates from
norm is worth a lot more than past behavior
Machine Generated Forecasts
Time Series Forecasting:	

ARIMA Models	

(AutoRegressive Integrated Moving Average)
Time Series Forecasts - ARIMA with Drift
ARIMA(3,1,1)(0,1,1)[12] with drift
Time Series Forecasts - ARIMA with Drift
ARIMA(3,1,1)(0,1,1)[12] with drift
Allow forecasts to
change over time
Number of periods	

per season.
}
}
Non-	

Seasonal	

Part
Seasonal	

Part
Time Series Forecasts - ARIMA with Drift
ARIMA(3,1,1)(0,1,1)[12] with drift
Allow forecasts to
change over time
Number of periods	

per season.
p = order of the autoregressive part;	

d = degree of first differencing involved;	

q = order of the moving average part.
}
}
Non-	

Seasonal	

Part
Seasonal	

Part
}
(p,d,q)
}
(p,d,q)
Time Series Forecasts - Auto Regression
In a multiple regression model, we forecast the variable of interest
using a linear combination of predictors. 	

!
vs	

!
In an autoregression model, we forecast the variable of interest using
a linear combination of past values of the variable 	

(regression of the variable against itself)
Time Series Forecasts - Auto Regression
In a multiple regression model, we forecast the variable of interest
using a linear combination of predictors. 	

!
vs	

!
In an autoregression model, we forecast the variable of interest using
a linear combination of past values of the variable 	

(regression of the variable against itself)
Order = no. of past values
Time Series Forecasts - Differencing
What we doing in (b) is differencing by computing the differences
between consecutive observations. 	

The goal is to eliminate trend and seasonality.
(a) Dow Jones index (b) Daily change in Dow Jones index
Time Series Forecasts - Differencing
What we doing in (b) is differencing by computing the differences
between consecutive observations. 	

(a) Dow Jones index (b) Daily change in Dow Jones index
Order = no. of difference needed
Time Series Forecasts - Moving Average
Rather than use past values of the forecast variable in a regression, a
moving average model uses past forecast errors in a regression-like
model (a weighted moving average of the past few forecast errors).
Time Series Forecasts - Moving Average
Rather than use past values of the forecast variable in a regression, a
moving average model uses past forecast errors in a regression-like
model (a weighted moving average of the past few forecast errors).
Order = no. of past values
Time Series Forecasts - ARIMA with Drift
ARIMA(3,1,1)(0,1,1)[12] with drift
Link to Seasonal ARIMA for
Forecasting Air Pollution Index:
A Case Study (Johor Malaysia)
Link to Seasonal ARIMA for
Forecasting Air Pollution Index:
A Case Study (Johor Malaysia)
ARIMA is one of the most popular time series forecasting methods. 	

It is very flexible and can handle complex scenarios
Time Series Forecasts - Comparison of Accuracy
Time Series Forecasts - Comparison of Accuracy
Kudos to the awesome designers on thenounproject.com
Folder by Christina W
Checklist by João Marcelo Ribeiro
Fence by José Hernandez
Robot by Simon Child
Conference by Wilson Joseph
Meeting by Olivier Guin
Employee Evaluation by Miroslav Koša
People by iconoci
STL
ARIMA
Holt-Winters

More Related Content

What's hot

Rational Sub-Grouping
Rational Sub-GroupingRational Sub-Grouping
Rational Sub-Grouping
Matt Hansen
 
Forecasting & time series data
Forecasting & time series dataForecasting & time series data
Forecasting & time series data
Jane Karla
 
Forecasting
ForecastingForecasting
MSA – Attribute ARR Test
MSA – Attribute ARR TestMSA – Attribute ARR Test
MSA – Attribute ARR Test
Matt Hansen
 
Exponential smoothing
Exponential smoothingExponential smoothing
Exponential smoothing
Jairo Moreno
 
Chap003 Forecasting
Chap003    ForecastingChap003    Forecasting
Chap003 Forecasting
Waqar Butt Vicky
 
Automatic algorithms for time series forecasting
Automatic algorithms for time series forecastingAutomatic algorithms for time series forecasting
Automatic algorithms for time series forecasting
Rob Hyndman
 
FORECASTING MODELS
FORECASTING MODELSFORECASTING MODELS
FORECASTING MODELS
AKHISHA P. A.
 
MSA – Gage R&R Test
MSA – Gage R&R TestMSA – Gage R&R Test
MSA – Gage R&R Test
Matt Hansen
 
Demand forecasting
Demand forecastingDemand forecasting
Demand forecasting
Prasanth Khanna
 
Identify Root Causes – Building the DCP
Identify Root Causes – Building the DCPIdentify Root Causes – Building the DCP
Identify Root Causes – Building the DCP
Matt Hansen
 
MSA – Improving the Measurement System
MSA – Improving the Measurement SystemMSA – Improving the Measurement System
MSA – Improving the Measurement System
Matt Hansen
 
Quantitative methods of demand forecasting
Quantitative methods of demand forecastingQuantitative methods of demand forecasting
Quantitative methods of demand forecasting
anithagrahalakshmi
 
ForecastIT 3. Simple Exponential Smoothing
ForecastIT 3. Simple Exponential SmoothingForecastIT 3. Simple Exponential Smoothing
ForecastIT 3. Simple Exponential Smoothing
DeepThought, Inc.
 
2b. forecasting linear trend
2b. forecasting   linear trend2b. forecasting   linear trend
2b. forecasting linear trend
Sudipta Saha
 
Variation Over Time (Short/Long Term Data)
Variation Over Time (Short/Long Term Data)Variation Over Time (Short/Long Term Data)
Variation Over Time (Short/Long Term Data)
Matt Hansen
 
Calculating a Sample Size
Calculating a Sample SizeCalculating a Sample Size
Calculating a Sample Size
Matt Hansen
 
Time Series Analysis: Theory and Practice
Time Series Analysis: Theory and PracticeTime Series Analysis: Theory and Practice
Time Series Analysis: Theory and Practice
Tetiana Ivanova
 
Shewhart
ShewhartShewhart
Shewhart
Thomas McNabb
 
ForecastIT 5. Winters' Exponential Smoothing
ForecastIT 5. Winters' Exponential SmoothingForecastIT 5. Winters' Exponential Smoothing
ForecastIT 5. Winters' Exponential Smoothing
DeepThought, Inc.
 

What's hot (20)

Rational Sub-Grouping
Rational Sub-GroupingRational Sub-Grouping
Rational Sub-Grouping
 
Forecasting & time series data
Forecasting & time series dataForecasting & time series data
Forecasting & time series data
 
Forecasting
ForecastingForecasting
Forecasting
 
MSA – Attribute ARR Test
MSA – Attribute ARR TestMSA – Attribute ARR Test
MSA – Attribute ARR Test
 
Exponential smoothing
Exponential smoothingExponential smoothing
Exponential smoothing
 
Chap003 Forecasting
Chap003    ForecastingChap003    Forecasting
Chap003 Forecasting
 
Automatic algorithms for time series forecasting
Automatic algorithms for time series forecastingAutomatic algorithms for time series forecasting
Automatic algorithms for time series forecasting
 
FORECASTING MODELS
FORECASTING MODELSFORECASTING MODELS
FORECASTING MODELS
 
MSA – Gage R&R Test
MSA – Gage R&R TestMSA – Gage R&R Test
MSA – Gage R&R Test
 
Demand forecasting
Demand forecastingDemand forecasting
Demand forecasting
 
Identify Root Causes – Building the DCP
Identify Root Causes – Building the DCPIdentify Root Causes – Building the DCP
Identify Root Causes – Building the DCP
 
MSA – Improving the Measurement System
MSA – Improving the Measurement SystemMSA – Improving the Measurement System
MSA – Improving the Measurement System
 
Quantitative methods of demand forecasting
Quantitative methods of demand forecastingQuantitative methods of demand forecasting
Quantitative methods of demand forecasting
 
ForecastIT 3. Simple Exponential Smoothing
ForecastIT 3. Simple Exponential SmoothingForecastIT 3. Simple Exponential Smoothing
ForecastIT 3. Simple Exponential Smoothing
 
2b. forecasting linear trend
2b. forecasting   linear trend2b. forecasting   linear trend
2b. forecasting linear trend
 
Variation Over Time (Short/Long Term Data)
Variation Over Time (Short/Long Term Data)Variation Over Time (Short/Long Term Data)
Variation Over Time (Short/Long Term Data)
 
Calculating a Sample Size
Calculating a Sample SizeCalculating a Sample Size
Calculating a Sample Size
 
Time Series Analysis: Theory and Practice
Time Series Analysis: Theory and PracticeTime Series Analysis: Theory and Practice
Time Series Analysis: Theory and Practice
 
Shewhart
ShewhartShewhart
Shewhart
 
ForecastIT 5. Winters' Exponential Smoothing
ForecastIT 5. Winters' Exponential SmoothingForecastIT 5. Winters' Exponential Smoothing
ForecastIT 5. Winters' Exponential Smoothing
 

Viewers also liked

forecast
forecastforecast
PyDataDC- Forecasting critical food violations at restaurants using open data
PyDataDC- Forecasting critical food violations at restaurants using open dataPyDataDC- Forecasting critical food violations at restaurants using open data
PyDataDC- Forecasting critical food violations at restaurants using open data
Nicole A. Donnelly, CMCP
 
Deductor Implementation Results
Deductor Implementation ResultsDeductor Implementation Results
Deductor Implementation ResultsKadimov Mansur
 
Shahid Lecture-9- MKAG1273
Shahid Lecture-9- MKAG1273Shahid Lecture-9- MKAG1273
Shahid Lecture-9- MKAG1273
nchakori
 
ForecastIT 7. Decomposition
ForecastIT 7. DecompositionForecastIT 7. Decomposition
ForecastIT 7. Decomposition
DeepThought, Inc.
 
Relat%c3%b3rio%20 final%20fgv%20sp
Relat%c3%b3rio%20 final%20fgv%20spRelat%c3%b3rio%20 final%20fgv%20sp
Relat%c3%b3rio%20 final%20fgv%20sp
arnaldoromera
 
BIM_2010_20_Bioinformatics_Project
BIM_2010_20_Bioinformatics_ProjectBIM_2010_20_Bioinformatics_Project
BIM_2010_20_Bioinformatics_Project
Sagar Nikam
 
Chapter 7
Chapter 7Chapter 7
Chapter 7
Vikas Agnihotri
 
ForecastIT 4. Holt's Exponential Smoothing
ForecastIT 4. Holt's Exponential SmoothingForecastIT 4. Holt's Exponential Smoothing
ForecastIT 4. Holt's Exponential Smoothing
DeepThought, Inc.
 
Business forecasting decomposition & exponential smoothing - bhawani nandan...
Business forecasting   decomposition & exponential smoothing - bhawani nandan...Business forecasting   decomposition & exponential smoothing - bhawani nandan...
Business forecasting decomposition & exponential smoothing - bhawani nandan...
Bhawani N Prasad
 
Moving Average
Moving AverageMoving Average
Moving Average
elboone
 
Chapter 13
Chapter 13Chapter 13
Time series Analysis & fpp package
Time series Analysis & fpp packageTime series Analysis & fpp package
Time series Analysis & fpp package
Dr. Fiona McGroarty
 
Trend adjusted exponential smoothing forecasting metho ds
Trend adjusted exponential smoothing forecasting metho dsTrend adjusted exponential smoothing forecasting metho ds
Trend adjusted exponential smoothing forecasting metho ds
Kiran Hanjar
 
Scipy 2011 Time Series Analysis in Python
Scipy 2011 Time Series Analysis in PythonScipy 2011 Time Series Analysis in Python
Scipy 2011 Time Series Analysis in Python
Wes McKinney
 
Forecasting-Exponential Smoothing
Forecasting-Exponential SmoothingForecasting-Exponential Smoothing
Forecasting-Exponential Smoothing
iceu novida adinata
 
Time series analysis
Time series analysisTime series analysis
Time series analysis
Faltu Focat
 
A General Framework for Enhancing Prediction Performance on Time Series Data
A General Framework for Enhancing Prediction Performance on Time Series DataA General Framework for Enhancing Prediction Performance on Time Series Data
A General Framework for Enhancing Prediction Performance on Time Series Data
HopeBay Technologies, Inc.
 
Classical decomposition
Classical decompositionClassical decomposition
Classical decomposition
Azzuriey Ahmad
 
Chapter 16
Chapter 16Chapter 16
Chapter 16
bmcfad01
 

Viewers also liked (20)

forecast
forecastforecast
forecast
 
PyDataDC- Forecasting critical food violations at restaurants using open data
PyDataDC- Forecasting critical food violations at restaurants using open dataPyDataDC- Forecasting critical food violations at restaurants using open data
PyDataDC- Forecasting critical food violations at restaurants using open data
 
Deductor Implementation Results
Deductor Implementation ResultsDeductor Implementation Results
Deductor Implementation Results
 
Shahid Lecture-9- MKAG1273
Shahid Lecture-9- MKAG1273Shahid Lecture-9- MKAG1273
Shahid Lecture-9- MKAG1273
 
ForecastIT 7. Decomposition
ForecastIT 7. DecompositionForecastIT 7. Decomposition
ForecastIT 7. Decomposition
 
Relat%c3%b3rio%20 final%20fgv%20sp
Relat%c3%b3rio%20 final%20fgv%20spRelat%c3%b3rio%20 final%20fgv%20sp
Relat%c3%b3rio%20 final%20fgv%20sp
 
BIM_2010_20_Bioinformatics_Project
BIM_2010_20_Bioinformatics_ProjectBIM_2010_20_Bioinformatics_Project
BIM_2010_20_Bioinformatics_Project
 
Chapter 7
Chapter 7Chapter 7
Chapter 7
 
ForecastIT 4. Holt's Exponential Smoothing
ForecastIT 4. Holt's Exponential SmoothingForecastIT 4. Holt's Exponential Smoothing
ForecastIT 4. Holt's Exponential Smoothing
 
Business forecasting decomposition & exponential smoothing - bhawani nandan...
Business forecasting   decomposition & exponential smoothing - bhawani nandan...Business forecasting   decomposition & exponential smoothing - bhawani nandan...
Business forecasting decomposition & exponential smoothing - bhawani nandan...
 
Moving Average
Moving AverageMoving Average
Moving Average
 
Chapter 13
Chapter 13Chapter 13
Chapter 13
 
Time series Analysis & fpp package
Time series Analysis & fpp packageTime series Analysis & fpp package
Time series Analysis & fpp package
 
Trend adjusted exponential smoothing forecasting metho ds
Trend adjusted exponential smoothing forecasting metho dsTrend adjusted exponential smoothing forecasting metho ds
Trend adjusted exponential smoothing forecasting metho ds
 
Scipy 2011 Time Series Analysis in Python
Scipy 2011 Time Series Analysis in PythonScipy 2011 Time Series Analysis in Python
Scipy 2011 Time Series Analysis in Python
 
Forecasting-Exponential Smoothing
Forecasting-Exponential SmoothingForecasting-Exponential Smoothing
Forecasting-Exponential Smoothing
 
Time series analysis
Time series analysisTime series analysis
Time series analysis
 
A General Framework for Enhancing Prediction Performance on Time Series Data
A General Framework for Enhancing Prediction Performance on Time Series DataA General Framework for Enhancing Prediction Performance on Time Series Data
A General Framework for Enhancing Prediction Performance on Time Series Data
 
Classical decomposition
Classical decompositionClassical decomposition
Classical decomposition
 
Chapter 16
Chapter 16Chapter 16
Chapter 16
 

Similar to Forecasting Techniques - Data Science SG

Large Scale Automatic Forecasting for Millions of Forecasts
Large Scale Automatic Forecasting for Millions of ForecastsLarge Scale Automatic Forecasting for Millions of Forecasts
Large Scale Automatic Forecasting for Millions of Forecasts
Ajay Ohri
 
Forecasting Models & Their Applications
Forecasting Models & Their ApplicationsForecasting Models & Their Applications
Forecasting Models & Their Applications
Mahmudul Hasan
 
Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model
AkarshAvinash
 
Time Series Analysis - 2 | Time Series in R | ARIMA Model Forecasting | Data ...
Time Series Analysis - 2 | Time Series in R | ARIMA Model Forecasting | Data ...Time Series Analysis - 2 | Time Series in R | ARIMA Model Forecasting | Data ...
Time Series Analysis - 2 | Time Series in R | ARIMA Model Forecasting | Data ...
Simplilearn
 
Ecm time series forecast
Ecm time series forecastEcm time series forecast
Ecm time series forecast
Ayapparaj SKS
 
Different Models Used In Time Series - InsideAIML
Different Models Used In Time Series - InsideAIMLDifferent Models Used In Time Series - InsideAIML
Different Models Used In Time Series - InsideAIML
VijaySharma802
 
Forecasting
ForecastingForecasting
Forecasting
Pradeep Kumar
 
Auto-Train a Time-Series Forecast Model With AML + ADB
Auto-Train a Time-Series Forecast Model With AML + ADBAuto-Train a Time-Series Forecast Model With AML + ADB
Auto-Train a Time-Series Forecast Model With AML + ADB
Databricks
 
Service Management: Forecasting Hydrogen Demand
Service Management: Forecasting Hydrogen DemandService Management: Forecasting Hydrogen Demand
Service Management: Forecasting Hydrogen Demand
irrosennen
 
Time series
Time seriesTime series
Time series
Haitham Ahmed
 
Forecasting_CO2_Emissions.pptx
Forecasting_CO2_Emissions.pptxForecasting_CO2_Emissions.pptx
Forecasting_CO2_Emissions.pptx
MOINDALVS
 
Forecasting Techniques
Forecasting TechniquesForecasting Techniques
Forecasting Techniques
Anand Subramaniam
 
Forecasting Techniques
Forecasting TechniquesForecasting Techniques
Forecasting Techniques
guest865c0e0c
 
2a. forecasting
2a. forecasting2a. forecasting
2a. forecasting
Sudipta Saha
 
ADaM datasets for graphs (paper)
ADaM datasets for graphs (paper)ADaM datasets for graphs (paper)
ADaM datasets for graphs (paper)
Kevin Lee
 
timeseries cheat sheet with example code for R
timeseries cheat sheet with example code for Rtimeseries cheat sheet with example code for R
timeseries cheat sheet with example code for R
derekjohnson549253
 
Time series deep learning
Time series   deep learningTime series   deep learning
Time series deep learning
Alberto Arrigoni
 
ARIMA.pptx
ARIMA.pptxARIMA.pptx
Time Series Anomaly Detection with .net and Azure
Time Series Anomaly Detection with .net and AzureTime Series Anomaly Detection with .net and Azure
Time Series Anomaly Detection with .net and Azure
Marco Parenzan
 
Product Design Forecasting Techniquesision.ppt
Product Design Forecasting Techniquesision.pptProduct Design Forecasting Techniquesision.ppt
Product Design Forecasting Techniquesision.ppt
avidc1000
 

Similar to Forecasting Techniques - Data Science SG (20)

Large Scale Automatic Forecasting for Millions of Forecasts
Large Scale Automatic Forecasting for Millions of ForecastsLarge Scale Automatic Forecasting for Millions of Forecasts
Large Scale Automatic Forecasting for Millions of Forecasts
 
Forecasting Models & Their Applications
Forecasting Models & Their ApplicationsForecasting Models & Their Applications
Forecasting Models & Their Applications
 
Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model
 
Time Series Analysis - 2 | Time Series in R | ARIMA Model Forecasting | Data ...
Time Series Analysis - 2 | Time Series in R | ARIMA Model Forecasting | Data ...Time Series Analysis - 2 | Time Series in R | ARIMA Model Forecasting | Data ...
Time Series Analysis - 2 | Time Series in R | ARIMA Model Forecasting | Data ...
 
Ecm time series forecast
Ecm time series forecastEcm time series forecast
Ecm time series forecast
 
Different Models Used In Time Series - InsideAIML
Different Models Used In Time Series - InsideAIMLDifferent Models Used In Time Series - InsideAIML
Different Models Used In Time Series - InsideAIML
 
Forecasting
ForecastingForecasting
Forecasting
 
Auto-Train a Time-Series Forecast Model With AML + ADB
Auto-Train a Time-Series Forecast Model With AML + ADBAuto-Train a Time-Series Forecast Model With AML + ADB
Auto-Train a Time-Series Forecast Model With AML + ADB
 
Service Management: Forecasting Hydrogen Demand
Service Management: Forecasting Hydrogen DemandService Management: Forecasting Hydrogen Demand
Service Management: Forecasting Hydrogen Demand
 
Time series
Time seriesTime series
Time series
 
Forecasting_CO2_Emissions.pptx
Forecasting_CO2_Emissions.pptxForecasting_CO2_Emissions.pptx
Forecasting_CO2_Emissions.pptx
 
Forecasting Techniques
Forecasting TechniquesForecasting Techniques
Forecasting Techniques
 
Forecasting Techniques
Forecasting TechniquesForecasting Techniques
Forecasting Techniques
 
2a. forecasting
2a. forecasting2a. forecasting
2a. forecasting
 
ADaM datasets for graphs (paper)
ADaM datasets for graphs (paper)ADaM datasets for graphs (paper)
ADaM datasets for graphs (paper)
 
timeseries cheat sheet with example code for R
timeseries cheat sheet with example code for Rtimeseries cheat sheet with example code for R
timeseries cheat sheet with example code for R
 
Time series deep learning
Time series   deep learningTime series   deep learning
Time series deep learning
 
ARIMA.pptx
ARIMA.pptxARIMA.pptx
ARIMA.pptx
 
Time Series Anomaly Detection with .net and Azure
Time Series Anomaly Detection with .net and AzureTime Series Anomaly Detection with .net and Azure
Time Series Anomaly Detection with .net and Azure
 
Product Design Forecasting Techniquesision.ppt
Product Design Forecasting Techniquesision.pptProduct Design Forecasting Techniquesision.ppt
Product Design Forecasting Techniquesision.ppt
 

Recently uploaded

06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
Timothy Spann
 
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
v7oacc3l
 
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
nyfuhyz
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
Sachin Paul
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
nuttdpt
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
nuttdpt
 
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
apvysm8
 
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
g4dpvqap0
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
sameer shah
 
Experts live - Improving user adoption with AI
Experts live - Improving user adoption with AIExperts live - Improving user adoption with AI
Experts live - Improving user adoption with AI
jitskeb
 
A presentation that explain the Power BI Licensing
A presentation that explain the Power BI LicensingA presentation that explain the Power BI Licensing
A presentation that explain the Power BI Licensing
AlessioFois2
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
aqzctr7x
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
Timothy Spann
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
bopyb
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
74nqk8xf
 
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
zsjl4mimo
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
manishkhaire30
 
University of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma TranscriptUniversity of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma Transcript
soxrziqu
 
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
74nqk8xf
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
AndrzejJarynowski
 

Recently uploaded (20)

06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM
 
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
在线办理(英国UCA毕业证书)创意艺术大学毕业证在读证明一模一样
 
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
 
Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......Palo Alto Cortex XDR presentation .......
Palo Alto Cortex XDR presentation .......
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
 
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
一比一原版(UCSF文凭证书)旧金山分校毕业证如何办理
 
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
办(uts毕业证书)悉尼科技大学毕业证学历证书原版一模一样
 
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
一比一原版(Glasgow毕业证书)格拉斯哥大学毕业证如何办理
 
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
 
Experts live - Improving user adoption with AI
Experts live - Improving user adoption with AIExperts live - Improving user adoption with AI
Experts live - Improving user adoption with AI
 
A presentation that explain the Power BI Licensing
A presentation that explain the Power BI LicensingA presentation that explain the Power BI Licensing
A presentation that explain the Power BI Licensing
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
 
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
一比一原版(GWU,GW文凭证书)乔治·华盛顿大学毕业证如何办理
 
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
一比一原版(牛布毕业证书)牛津布鲁克斯大学毕业证如何办理
 
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
一比一原版(Harvard毕业证书)哈佛大学毕业证如何办理
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
 
University of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma TranscriptUniversity of New South Wales degree offer diploma Transcript
University of New South Wales degree offer diploma Transcript
 
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
一比一原版(Coventry毕业证书)考文垂大学毕业证如何办理
 
Intelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicineIntelligence supported media monitoring in veterinary medicine
Intelligence supported media monitoring in veterinary medicine
 

Forecasting Techniques - Data Science SG

  • 1. Learnings from Forecasting - Principles and Practice
  • 3. Basic Modeling Intro & simple theory Forecasting Forecast+Model www.otexts.org/fpp
  • 4. Code at: https://github.com/thiakx/Forecasting_DSSG Adapted from the Forecasting: Principles and Practice book
  • 5.
  • 6. Judgmental Forecasts Machine Generated Forecasts
  • 8. Judgmental Forecasts - Principles Set the forecasting task clearly and concisely Implement a systematic approach: -Document and justify -Systematically evaluate forecasts Segregate forecasters and users
  • 9. Judgmental Forecasts - How to Delphi Method - Panel of experts Ask the executives, staff, customers Use a proxy (similar cases, best / worst case)
  • 10.
  • 12.
  • 13.
  • 14.
  • 16. The Basics -Time Series Decomposition
  • 18. The Basics - Seasonality +Trend
  • 19. The Basics - Remainder / Random Error
  • 20. The Basics - Seasonal sub-series plot
  • 22. The Basics -Time Series Decomposition then re-seasonalize with thisTrain model with this
  • 23. The Basics -Time Series Decomposition then re-seasonalize with thisTrain model with this
  • 24. The Basics -Time Series Decomposition 95% confidence 80% confidence then re-seasonalize with thisTrain model with this
  • 25. The Basics -Time Series Decomposition then re-seasonalize with thisTrain model with this
  • 26. Seasonal andTrend decomposition using Loess (STL) code
  • 27. Córdoba Using seasonal-trend decomposition based on loess (STL) to explore temporal patterns of pneumonic lesions in finishing pigs slaughtered in England, 2005–2011
  • 28. Córdoba Using seasonal-trend decomposition based on loess (STL) to explore temporal patterns of pneumonic lesions in finishing pigs slaughtered in England, 2005–2011 STL is suitable as the overall trend fluctuates a fair bit
  • 29. Machine Generated Forecasts Time Series Forecasting: Exponential smoothing
  • 30. Time Series Forecasts - Holts-Winters
  • 31. Time Series Forecasts - Exponential Smoothing
  • 32. Time Series Forecasts - Exponential Smoothing More relevantLess relevant Something to represent fall in relevance?
  • 33. Time Series Forecasts - Exponential Smoothing Smoothing Parameter α = 0.8 0.8 0.16 0.032 0.064 T1 T2 T3 T4 T1-T4
  • 34. Time Series Forecasts - Exponential Smoothing T1-T4 Smoothing Parameter α = decided by minimizing error rate
  • 35. Time Series Forecasts - Damping Undamped projection Damped projection
  • 36. Time Series Forecasts - Additive vs Multiplicative The additive method is preferred when the seasonal variations are roughly constant through the series, while the multiplicative method is preferred when the seasonal variations are changing proportional to the level of the series.
  • 37. Time Series Forecasts - Holts-Winters
  • 38. Link to: Usage of Modified Holt-Winters Method in the Anomaly Detection of NetworkTraffic: Case Studies
  • 39. Link to: Usage of Modified Holt-Winters Method in the Anomaly Detection of NetworkTraffic: Case Studies Holt-Winter is suitable as the most recent behavior that deviates from norm is worth a lot more than past behavior
  • 40. Machine Generated Forecasts Time Series Forecasting: ARIMA Models (AutoRegressive Integrated Moving Average)
  • 41. Time Series Forecasts - ARIMA with Drift ARIMA(3,1,1)(0,1,1)[12] with drift
  • 42. Time Series Forecasts - ARIMA with Drift ARIMA(3,1,1)(0,1,1)[12] with drift Allow forecasts to change over time Number of periods per season. } } Non- Seasonal Part Seasonal Part
  • 43. Time Series Forecasts - ARIMA with Drift ARIMA(3,1,1)(0,1,1)[12] with drift Allow forecasts to change over time Number of periods per season. p = order of the autoregressive part; d = degree of first differencing involved; q = order of the moving average part. } } Non- Seasonal Part Seasonal Part } (p,d,q) } (p,d,q)
  • 44. Time Series Forecasts - Auto Regression In a multiple regression model, we forecast the variable of interest using a linear combination of predictors. ! vs ! In an autoregression model, we forecast the variable of interest using a linear combination of past values of the variable (regression of the variable against itself)
  • 45. Time Series Forecasts - Auto Regression In a multiple regression model, we forecast the variable of interest using a linear combination of predictors. ! vs ! In an autoregression model, we forecast the variable of interest using a linear combination of past values of the variable (regression of the variable against itself) Order = no. of past values
  • 46. Time Series Forecasts - Differencing What we doing in (b) is differencing by computing the differences between consecutive observations. The goal is to eliminate trend and seasonality. (a) Dow Jones index (b) Daily change in Dow Jones index
  • 47. Time Series Forecasts - Differencing What we doing in (b) is differencing by computing the differences between consecutive observations. (a) Dow Jones index (b) Daily change in Dow Jones index Order = no. of difference needed
  • 48. Time Series Forecasts - Moving Average Rather than use past values of the forecast variable in a regression, a moving average model uses past forecast errors in a regression-like model (a weighted moving average of the past few forecast errors).
  • 49. Time Series Forecasts - Moving Average Rather than use past values of the forecast variable in a regression, a moving average model uses past forecast errors in a regression-like model (a weighted moving average of the past few forecast errors). Order = no. of past values
  • 50. Time Series Forecasts - ARIMA with Drift ARIMA(3,1,1)(0,1,1)[12] with drift
  • 51. Link to Seasonal ARIMA for Forecasting Air Pollution Index: A Case Study (Johor Malaysia)
  • 52. Link to Seasonal ARIMA for Forecasting Air Pollution Index: A Case Study (Johor Malaysia) ARIMA is one of the most popular time series forecasting methods. It is very flexible and can handle complex scenarios
  • 53. Time Series Forecasts - Comparison of Accuracy
  • 54. Time Series Forecasts - Comparison of Accuracy
  • 55.
  • 56. Kudos to the awesome designers on thenounproject.com Folder by Christina W Checklist by João Marcelo Ribeiro Fence by José Hernandez Robot by Simon Child Conference by Wilson Joseph Meeting by Olivier Guin Employee Evaluation by Miroslav Koša People by iconoci STL ARIMA Holt-Winters