SlideShare ist ein Scribd-Unternehmen logo
1 von 12
Downloaden Sie, um offline zu lesen
ARIMA	
  FORECASTING	
  
ALGORITHM	
  
1
Team	
  Members:	
  
Sera	
  Crasta	
  
Nora	
  Alosaimi	
  
Puneet	
  Mahana	
  
SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015	
  
Defini5on	
  
ARIMA	
  -­‐	
  (A)uto(R)egressive	
  (I)ntegrated	
  (M)oving	
  (A)verage	
  models.	
  
	
  
• Auto	
  Regressive	
  –	
  dependency	
  of	
  a	
  value	
  of	
  a	
  dataset	
  on	
  combinaKon	
  of	
  previous	
  values	
  of	
  the	
  same	
  
dataset	
  
• Integrated	
  –	
  CombinaKon	
  
• Moving	
  average	
  –	
  analysing	
  past	
  forecast	
  errors	
  to	
  predict	
  future	
  values	
  
	
  
	
  
A	
  forecasKng	
  technique	
  thus	
  projects	
  the	
  future	
  values	
  of	
  a	
  series	
  based	
  enKrely	
  on	
  its	
  own	
  inerKa.	
  
SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  2	
  
Why	
  is	
  Arima	
  	
  Forecas5ng	
  important?	
  
•  Businesses	
  need	
  to	
  adjust	
  with	
  changing	
  market	
  trends	
  and	
  thus	
  its	
  management	
  need	
  to	
  predict	
  
what	
  may	
  happen	
  in	
  future	
  with	
  greater	
  accuracy	
  to	
  avoid	
  losses.	
  
•  TradiKonal	
  methods	
  –	
  expert	
  advice,	
  panel	
  discussions.	
  
•  QuanKtaKve	
  Method	
  –	
  Arima	
  ForecasKng.	
  
•  EsKmaKng	
  the	
  Kme	
  delays/	
  lags	
  in	
  the	
  ongoing	
  processes.	
  
•  ForecasKng	
  the	
  economic	
  growth.	
  
•  Models	
  relaKonships	
  using	
  data	
  collected	
  over	
  Kme	
  -­‐	
  prices,	
  GDP,	
  quanKKes,	
  sales.	
  
SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  3	
  
Algorithm	
  Outline	
  	
  
	
  
Arima	
  Forecas5ng	
  approach:	
  
	
  
1.  Choose	
   a	
   dataset	
   to	
   be	
   forecasted	
   and	
   plot	
   the	
  	
  	
  	
  
data	
  against	
  Kme.	
  
2.  Analyse	
  the	
  plot	
  to	
  see	
  if	
  it	
  is	
  staKonary	
  with	
  Kme.	
  
3.  If	
   necessary,	
   difference	
   the	
   data	
   unKl	
   it	
   appears	
  
staKonary	
  
4.  	
   Plot	
   autocorrelaKon(ACF)	
   and	
   parKal	
  	
  
autocorrelaKon(PACF)	
  of	
  the	
  differenced	
  data	
  and	
  
esKmate	
  possible	
  model	
  parameters	
  
5. Calculate	
   AIC	
   values	
   for	
   all	
   model	
   parameters	
   to	
  
search	
  for	
  be^er	
  model	
  
6. Plot	
  the	
  residual	
  of	
  the	
  model	
  parameters	
  obtained	
  
to	
  verify	
  that	
  no	
  lag	
  occurs	
  for	
  them.	
  
7. If	
   lag	
   occurs	
   in	
   residual	
   plot,	
   try	
   another	
  
esKmated	
   model	
   parameters	
   unKl	
   we	
   get	
   a	
  
good	
  residual	
  plot.	
  
8. Once	
   a	
   good	
   residual	
   is	
   obtained,	
   calculate	
  
forecast.	
  
SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  4	
  
Algorithm	
  Pseudo	
  Code	
  
	
   1.Plot(dataset)	
  	
  
	
  while(graph	
  is	
  non-­‐staKonary	
  =	
  True)	
  
	
   	
  {smoothen	
  graph	
  to	
  make	
  it	
  staKonary}	
  
	
  
	
   2.	
  ACF/PACF(StaKonary	
  Graph)	
  
	
   3.	
  EsKmate	
  all	
  possible	
  model	
  parameters	
  
	
   4.	
  Calculate	
  AIC	
  values	
  of	
  all	
  model	
  parameters	
  
	
  
	
   5.	
  plot	
  (residual	
  of	
  model	
  parameters)	
  
	
  if(residual	
  graph	
  with	
  no	
  lag)	
  
	
   	
  {Forecast	
  Dataset	
  with	
  these	
  parameters}	
  
	
  else	
  choose	
  other	
  esKmated	
  model	
  parameters	
  and	
  repeat	
  step	
  3	
  
	
  
	
  
SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  5	
  
Forecas5ng	
  Result	
  	
  
	
  
	
  
SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  6	
  
Comparing	
  Arima	
  with	
  other	
  techniques	
  
SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  7	
  
Forecast  Accuracy  Results
SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  8	
  
METHOD	
   Mean	
  	
  
error	
  
Root	
  mean	
  	
  
square	
  	
  
error	
  
Mean	
  	
  
absolute	
  	
  
error	
  
Mean	
  	
  
absolute	
  	
  
scaled	
  error	
  
Mean	
   9.128060	
   756.3431	
   619.3957	
   1.739531	
  
Naive	
   11.2086	
   495.6456	
   356.0705	
   1.000000	
  
Drie	
   -­‐2.002087	
   496.345	
   358.0791	
   1.005641	
  
Arima	
   6.649148	
   324.172	
   243.8181	
   0.7016939	
  
Conclusions	
  
Arima	
  Algorithm:	
  
• 	
  Arima	
  technique	
  is	
  more	
  accurate	
  than	
  tradiKonal	
  forecasKng	
  techniques.	
  
•  PracKcal	
  and	
  useful.	
  	
  
LimitaKon:	
  
•  Require	
  historical	
  data	
  –	
  the	
  larger	
  the	
  dataset,	
  the	
  be^er	
  the	
  forecast	
  
	
  
ApplicaKon:	
  	
  
•  Manufacturing	
  Industry.	
  
•  Sales	
  department.	
  	
  
•  Finance	
  Department.	
  
SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  9	
  
Appendix	
  
	
   Source	
  Code:	
  
	
   For	
  non-­‐seasonal	
  dataset	
  
	
   Arima	
  (p,	
  d,	
  q)	
  where	
  p,	
  d,	
  q	
  are	
  model	
  parameters	
  
	
   For	
  Seasonal	
  Dataset	
  
	
   Arima	
  (p,	
  d,	
  q)	
  (P,	
  D,	
  Q)	
  where	
  p,	
  d,	
  q	
  are	
  non	
  seasonal	
  parameters	
  and	
  P,	
  D,	
  Q	
  are	
  seasonal	
  parameters	
  
	
  
	
  
	
  
	
  
	
  
	
  
	
  
	
  
	
  SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  10	
  
Appendix	
  
Arima	
  Forecas5ng	
  in	
  R	
  
	
   library(forecast)	
  
	
   library(fpp)	
  
	
  	
  #forecas5ng	
  
	
   plot(sunspotarea,	
  main=	
  "	
  Original	
  Dataset")	
  
	
   sunspotarea1=diff(sunspotarea)	
  
	
   plot(sunspotarea1)	
  
	
   acf(sunspotarea1)	
  
	
   acf(sunspotarea1,	
  plot=FALSE)	
  
	
   pacf(sunspotarea1)	
  
	
   pacf(sunspotarea1,	
  plot=FALSE)	
  
	
   fit<-­‐Arima(sunspotarea,	
  order=c(2,1,5))	
  
	
   tsdisplay(residuals(fit))	
  
plot(forecast(fit,	
  h=25),	
  main="ARIMA	
  
FORECASTING",	
  xlab="Kme",	
  ylab="sunspotarea")	
  
	
  
#Accuracy	
  checking	
  
	
   sun	
  <-­‐	
  window(sunspotarea,	
  end=2000)	
  
	
   plot(sun,	
  xlim=c(1874,2015))	
  
	
   lines(meanf(sun,h=15)$mean,	
  col=4)	
  
	
   lines(rwf(sun,h=15)$mean,	
  col=2)	
  
	
   lines(rwf(sun,drie=TRUE,h=15)$mean,	
  col=3)	
  
	
   legend("toplee",	
  lty=1,	
  col=c(4,2,3),	
  
	
   	
  	
  	
  	
  	
  	
  	
  legend=c("Mean	
  method","Naive	
  method","Drie	
  
method"))	
  
	
   lines(sunspotarea)	
  
	
  
	
  
	
  SERA/NORA/PUNEET	
   	
   	
   	
  CS6212/ARORA/FALL	
  2015 	
   	
   	
  11	
  
Thank	
  you	
  	
  





SERA/NORA/PUNEET	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  CS6212/ARORA/FALL	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  	
  12	
  	
  	
  	
  	
  	
  	
  	
  

Weitere ähnliche Inhalte

Was ist angesagt?

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
 
Time Series Analysis - 1 | Time Series in R | Time Series Forecasting | Data ...
Time Series Analysis - 1 | Time Series in R | Time Series Forecasting | Data ...Time Series Analysis - 1 | Time Series in R | Time Series Forecasting | Data ...
Time Series Analysis - 1 | Time Series in R | Time Series Forecasting | Data ...
Simplilearn
 
Autoregression
AutoregressionAutoregression
Autoregression
jchristo06
 

Was ist angesagt? (20)

Time series forecasting
Time series forecastingTime series forecasting
Time series forecasting
 
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 ...
 
ARIMA
ARIMA ARIMA
ARIMA
 
Presentation
PresentationPresentation
Presentation
 
Time Series Forecasting Project Presentation.
Time Series Forecasting Project  Presentation.Time Series Forecasting Project  Presentation.
Time Series Forecasting Project Presentation.
 
Data Science - Part X - Time Series Forecasting
Data Science - Part X - Time Series ForecastingData Science - Part X - Time Series Forecasting
Data Science - Part X - Time Series Forecasting
 
ARIMA Models - [Lab 3]
ARIMA Models - [Lab 3]ARIMA Models - [Lab 3]
ARIMA Models - [Lab 3]
 
Seasonal ARIMA
Seasonal ARIMASeasonal ARIMA
Seasonal ARIMA
 
Time Series Analysis - 1 | Time Series in R | Time Series Forecasting | Data ...
Time Series Analysis - 1 | Time Series in R | Time Series Forecasting | Data ...Time Series Analysis - 1 | Time Series in R | Time Series Forecasting | Data ...
Time Series Analysis - 1 | Time Series in R | Time Series Forecasting | Data ...
 
Trend analysis and time Series Analysis
Trend analysis and time Series Analysis Trend analysis and time Series Analysis
Trend analysis and time Series Analysis
 
Arima model
Arima modelArima model
Arima model
 
Time series
Time seriesTime series
Time series
 
Lesson 4 ar-ma
Lesson 4 ar-maLesson 4 ar-ma
Lesson 4 ar-ma
 
Time Series Decomposition
Time Series DecompositionTime Series Decomposition
Time Series Decomposition
 
AR model
AR modelAR model
AR model
 
Autoregression
AutoregressionAutoregression
Autoregression
 
Time Series, Moving Average
Time Series, Moving AverageTime Series, Moving Average
Time Series, Moving Average
 
Time series analysis 101
Time series analysis 101Time series analysis 101
Time series analysis 101
 
Time series.ppt
Time series.pptTime series.ppt
Time series.ppt
 
Machine learning: Stock Price Prediction
Machine learning: Stock Price PredictionMachine learning: Stock Price Prediction
Machine learning: Stock Price Prediction
 

Andere mochten auch

Time Series
Time SeriesTime Series
Time Series
yush313
 
Arima model-uygulamalı-ekonometri
Arima model-uygulamalı-ekonometriArima model-uygulamalı-ekonometri
Arima model-uygulamalı-ekonometri
Burhanettin NOĞAY
 

Andere mochten auch (19)

Time Series
Time SeriesTime Series
Time Series
 
Time Series Analysis Ravi
Time Series Analysis RaviTime Series Analysis Ravi
Time Series Analysis Ravi
 
time series analysis
time series analysistime series analysis
time series analysis
 
Time Series Analysis - Modeling and Forecasting
Time Series Analysis - Modeling and ForecastingTime Series Analysis - Modeling and Forecasting
Time Series Analysis - Modeling and Forecasting
 
Gold Price Forecasting
Gold Price ForecastingGold Price Forecasting
Gold Price Forecasting
 
Time series slideshare
Time series slideshareTime series slideshare
Time series slideshare
 
HR Practices in Kerala Automobiles Limited (KAL)
HR Practices in Kerala Automobiles Limited (KAL)HR Practices in Kerala Automobiles Limited (KAL)
HR Practices in Kerala Automobiles Limited (KAL)
 
Arima model-uygulamalı-ekonometri
Arima model-uygulamalı-ekonometriArima model-uygulamalı-ekonometri
Arima model-uygulamalı-ekonometri
 
58604684 kerala-automobiles-ltd
58604684 kerala-automobiles-ltd58604684 kerala-automobiles-ltd
58604684 kerala-automobiles-ltd
 
Stopping Rule for Secretory Problem - Presentation by Haoyang Tian, Wesam Als...
Stopping Rule for Secretory Problem - Presentation by Haoyang Tian, Wesam Als...Stopping Rule for Secretory Problem - Presentation by Haoyang Tian, Wesam Als...
Stopping Rule for Secretory Problem - Presentation by Haoyang Tian, Wesam Als...
 
Proof of Cook Levin Theorem (Presentation by Xiechuan, Song and Shuo)
Proof of Cook Levin Theorem (Presentation by Xiechuan, Song and Shuo)Proof of Cook Levin Theorem (Presentation by Xiechuan, Song and Shuo)
Proof of Cook Levin Theorem (Presentation by Xiechuan, Song and Shuo)
 
1634 time series and trend analysis
1634 time series and trend analysis1634 time series and trend analysis
1634 time series and trend analysis
 
Proof of O(log *n) time complexity of Union find (Presentation by Wei Li, Zeh...
Proof of O(log *n) time complexity of Union find (Presentation by Wei Li, Zeh...Proof of O(log *n) time complexity of Union find (Presentation by Wei Li, Zeh...
Proof of O(log *n) time complexity of Union find (Presentation by Wei Li, Zeh...
 
Using Salesforce, ERP, Tableau & R in Sales Forecasting
Using Salesforce, ERP, Tableau & R in Sales ForecastingUsing Salesforce, ERP, Tableau & R in Sales Forecasting
Using Salesforce, ERP, Tableau & R in Sales Forecasting
 
Bron Kerbosch Algorithm - Presentation by Jun Zhai, Tianhang Qiang and Yizhen...
Bron Kerbosch Algorithm - Presentation by Jun Zhai, Tianhang Qiang and Yizhen...Bron Kerbosch Algorithm - Presentation by Jun Zhai, Tianhang Qiang and Yizhen...
Bron Kerbosch Algorithm - Presentation by Jun Zhai, Tianhang Qiang and Yizhen...
 
NP-Completeness - II
NP-Completeness - IINP-Completeness - II
NP-Completeness - II
 
Time Series Analysis/ Forecasting
Time Series Analysis/ Forecasting  Time Series Analysis/ Forecasting
Time Series Analysis/ Forecasting
 
Using Decision trees with GIS data for modeling and prediction
Using Decision trees with GIS data for modeling and prediction Using Decision trees with GIS data for modeling and prediction
Using Decision trees with GIS data for modeling and prediction
 
Algorithmic Puzzles
Algorithmic PuzzlesAlgorithmic Puzzles
Algorithmic Puzzles
 

Ähnlich wie Arima Forecasting - Presentation by Sera Cresta, Nora Alosaimi and Puneet Mahana

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
 
Forecasting%20Economic%20Series%20using%20ARMA
Forecasting%20Economic%20Series%20using%20ARMAForecasting%20Economic%20Series%20using%20ARMA
Forecasting%20Economic%20Series%20using%20ARMA
Nagendra Belvadi
 
Writing Sample
Writing SampleWriting Sample
Writing Sample
Yiqun Li
 

Ähnlich wie Arima Forecasting - Presentation by Sera Cresta, Nora Alosaimi and Puneet Mahana (20)

Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model Air Passenger Prediction Using ARIMA Model
Air Passenger Prediction Using ARIMA Model
 
SAP HANA SPS09 - Predictive Analysis Library
SAP HANA SPS09 - Predictive Analysis LibrarySAP HANA SPS09 - Predictive Analysis Library
SAP HANA SPS09 - Predictive Analysis Library
 
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
 
IRJET- Analysis of Crucial Oil Gas and Liquid Sensor Statistics and Productio...
IRJET- Analysis of Crucial Oil Gas and Liquid Sensor Statistics and Productio...IRJET- Analysis of Crucial Oil Gas and Liquid Sensor Statistics and Productio...
IRJET- Analysis of Crucial Oil Gas and Liquid Sensor Statistics and Productio...
 
Forecasting%20Economic%20Series%20using%20ARMA
Forecasting%20Economic%20Series%20using%20ARMAForecasting%20Economic%20Series%20using%20ARMA
Forecasting%20Economic%20Series%20using%20ARMA
 
What is ARIMA Forecasting and How Can it Be Used for Enterprise Analysis?
What is ARIMA Forecasting and How Can it Be Used for Enterprise Analysis?What is ARIMA Forecasting and How Can it Be Used for Enterprise Analysis?
What is ARIMA Forecasting and How Can it Be Used for Enterprise Analysis?
 
SPC (Statistical Process Control) concepts in forecasting
SPC (Statistical Process Control) concepts in forecastingSPC (Statistical Process Control) concepts in forecasting
SPC (Statistical Process Control) concepts in forecasting
 
Cpk problem solving_pcba smt machine
Cpk problem solving_pcba smt machineCpk problem solving_pcba smt machine
Cpk problem solving_pcba smt machine
 
Writing Sample
Writing SampleWriting Sample
Writing Sample
 
APO Overview with SNP Basics.ppt
APO Overview with SNP Basics.pptAPO Overview with SNP Basics.ppt
APO Overview with SNP Basics.ppt
 
Ecm time series forecast
Ecm time series forecastEcm time series forecast
Ecm time series forecast
 
A study of the Behavior of Floating-Point Errors
A study of the Behavior of Floating-Point ErrorsA study of the Behavior of Floating-Point Errors
A study of the Behavior of Floating-Point Errors
 
Time series modelling arima-arch
Time series modelling  arima-archTime series modelling  arima-arch
Time series modelling arima-arch
 
Fraud Detection in Financial Services using Graph Analysis and Machine Learning
Fraud Detection in Financial Services using Graph Analysis and Machine LearningFraud Detection in Financial Services using Graph Analysis and Machine Learning
Fraud Detection in Financial Services using Graph Analysis and Machine Learning
 
FMEA training (AIAG VDA Edition 01)
FMEA training (AIAG VDA Edition 01)FMEA training (AIAG VDA Edition 01)
FMEA training (AIAG VDA Edition 01)
 
SAP HANA SPS09 - Series Data
SAP HANA SPS09 - Series DataSAP HANA SPS09 - Series Data
SAP HANA SPS09 - Series Data
 
Anna Vergeles, Nataliia Manakova "Unsupervised Real-Time Stream-Based Novelty...
Anna Vergeles, Nataliia Manakova "Unsupervised Real-Time Stream-Based Novelty...Anna Vergeles, Nataliia Manakova "Unsupervised Real-Time Stream-Based Novelty...
Anna Vergeles, Nataliia Manakova "Unsupervised Real-Time Stream-Based Novelty...
 
Adaptive Query Optimization
Adaptive Query OptimizationAdaptive Query Optimization
Adaptive Query Optimization
 
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
IRJET- A Comparative Forecasting Analysis of ARIMA Model Vs Random Forest Alg...
IRJET- A Comparative Forecasting Analysis of ARIMA Model Vs Random Forest Alg...IRJET- A Comparative Forecasting Analysis of ARIMA Model Vs Random Forest Alg...
IRJET- A Comparative Forecasting Analysis of ARIMA Model Vs Random Forest Alg...
 

Mehr von Amrinder Arora

Mehr von Amrinder Arora (20)

Convex Hull - Chan's Algorithm O(n log h) - Presentation by Yitian Huang and ...
Convex Hull - Chan's Algorithm O(n log h) - Presentation by Yitian Huang and ...Convex Hull - Chan's Algorithm O(n log h) - Presentation by Yitian Huang and ...
Convex Hull - Chan's Algorithm O(n log h) - Presentation by Yitian Huang and ...
 
Graph Traversal Algorithms - Breadth First Search
Graph Traversal Algorithms - Breadth First SearchGraph Traversal Algorithms - Breadth First Search
Graph Traversal Algorithms - Breadth First Search
 
Graph Traversal Algorithms - Depth First Search Traversal
Graph Traversal Algorithms - Depth First Search TraversalGraph Traversal Algorithms - Depth First Search Traversal
Graph Traversal Algorithms - Depth First Search Traversal
 
Online algorithms in Machine Learning
Online algorithms in Machine LearningOnline algorithms in Machine Learning
Online algorithms in Machine Learning
 
NP completeness
NP completenessNP completeness
NP completeness
 
Euclid's Algorithm for Greatest Common Divisor - Time Complexity Analysis
Euclid's Algorithm for Greatest Common Divisor - Time Complexity AnalysisEuclid's Algorithm for Greatest Common Divisor - Time Complexity Analysis
Euclid's Algorithm for Greatest Common Divisor - Time Complexity Analysis
 
Dynamic Programming - Part II
Dynamic Programming - Part IIDynamic Programming - Part II
Dynamic Programming - Part II
 
Dynamic Programming - Part 1
Dynamic Programming - Part 1Dynamic Programming - Part 1
Dynamic Programming - Part 1
 
Greedy Algorithms
Greedy AlgorithmsGreedy Algorithms
Greedy Algorithms
 
Divide and Conquer - Part II - Quickselect and Closest Pair of Points
Divide and Conquer - Part II - Quickselect and Closest Pair of PointsDivide and Conquer - Part II - Quickselect and Closest Pair of Points
Divide and Conquer - Part II - Quickselect and Closest Pair of Points
 
Divide and Conquer - Part 1
Divide and Conquer - Part 1Divide and Conquer - Part 1
Divide and Conquer - Part 1
 
Asymptotic Notation and Data Structures
Asymptotic Notation and Data StructuresAsymptotic Notation and Data Structures
Asymptotic Notation and Data Structures
 
Introduction to Algorithms and Asymptotic Notation
Introduction to Algorithms and Asymptotic NotationIntroduction to Algorithms and Asymptotic Notation
Introduction to Algorithms and Asymptotic Notation
 
Set Operations - Union Find and Bloom Filters
Set Operations - Union Find and Bloom FiltersSet Operations - Union Find and Bloom Filters
Set Operations - Union Find and Bloom Filters
 
Binomial Heaps and Fibonacci Heaps
Binomial Heaps and Fibonacci HeapsBinomial Heaps and Fibonacci Heaps
Binomial Heaps and Fibonacci Heaps
 
R-Trees and Geospatial Data Structures
R-Trees and Geospatial Data StructuresR-Trees and Geospatial Data Structures
R-Trees and Geospatial Data Structures
 
Tries - Tree Based Structures for Strings
Tries - Tree Based Structures for StringsTries - Tree Based Structures for Strings
Tries - Tree Based Structures for Strings
 
Splay Trees and Self Organizing Data Structures
Splay Trees and Self Organizing Data StructuresSplay Trees and Self Organizing Data Structures
Splay Trees and Self Organizing Data Structures
 
BTrees - Great alternative to Red Black, AVL and other BSTs
BTrees - Great alternative to Red Black, AVL and other BSTsBTrees - Great alternative to Red Black, AVL and other BSTs
BTrees - Great alternative to Red Black, AVL and other BSTs
 
Binary Search Trees - AVL and Red Black
Binary Search Trees - AVL and Red BlackBinary Search Trees - AVL and Red Black
Binary Search Trees - AVL and Red Black
 

Kürzlich hochgeladen

Kürzlich hochgeladen (20)

Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptx
 
On_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptx
On_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptxOn_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptx
On_Translating_a_Tamil_Poem_by_A_K_Ramanujan.pptx
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - English
 
Towards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxTowards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptx
 
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptxCOMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
COMMUNICATING NEGATIVE NEWS - APPROACHES .pptx
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
How to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptxHow to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptx
 
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxHMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdf
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and Modifications
 
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdfUGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
UGC NET Paper 1 Mathematical Reasoning & Aptitude.pdf
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxHMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024
 
Fostering Friendships - Enhancing Social Bonds in the Classroom
Fostering Friendships - Enhancing Social Bonds  in the ClassroomFostering Friendships - Enhancing Social Bonds  in the Classroom
Fostering Friendships - Enhancing Social Bonds in the Classroom
 
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
 

Arima Forecasting - Presentation by Sera Cresta, Nora Alosaimi and Puneet Mahana

  • 1. ARIMA  FORECASTING   ALGORITHM   1 Team  Members:   Sera  Crasta   Nora  Alosaimi   Puneet  Mahana   SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015  
  • 2. Defini5on   ARIMA  -­‐  (A)uto(R)egressive  (I)ntegrated  (M)oving  (A)verage  models.     • Auto  Regressive  –  dependency  of  a  value  of  a  dataset  on  combinaKon  of  previous  values  of  the  same   dataset   • Integrated  –  CombinaKon   • Moving  average  –  analysing  past  forecast  errors  to  predict  future  values       A  forecasKng  technique  thus  projects  the  future  values  of  a  series  based  enKrely  on  its  own  inerKa.   SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      2  
  • 3. Why  is  Arima    Forecas5ng  important?   •  Businesses  need  to  adjust  with  changing  market  trends  and  thus  its  management  need  to  predict   what  may  happen  in  future  with  greater  accuracy  to  avoid  losses.   •  TradiKonal  methods  –  expert  advice,  panel  discussions.   •  QuanKtaKve  Method  –  Arima  ForecasKng.   •  EsKmaKng  the  Kme  delays/  lags  in  the  ongoing  processes.   •  ForecasKng  the  economic  growth.   •  Models  relaKonships  using  data  collected  over  Kme  -­‐  prices,  GDP,  quanKKes,  sales.   SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      3  
  • 4. Algorithm  Outline       Arima  Forecas5ng  approach:     1.  Choose   a   dataset   to   be   forecasted   and   plot   the         data  against  Kme.   2.  Analyse  the  plot  to  see  if  it  is  staKonary  with  Kme.   3.  If   necessary,   difference   the   data   unKl   it   appears   staKonary   4.    Plot   autocorrelaKon(ACF)   and   parKal     autocorrelaKon(PACF)  of  the  differenced  data  and   esKmate  possible  model  parameters   5. Calculate   AIC   values   for   all   model   parameters   to   search  for  be^er  model   6. Plot  the  residual  of  the  model  parameters  obtained   to  verify  that  no  lag  occurs  for  them.   7. If   lag   occurs   in   residual   plot,   try   another   esKmated   model   parameters   unKl   we   get   a   good  residual  plot.   8. Once   a   good   residual   is   obtained,   calculate   forecast.   SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      4  
  • 5. Algorithm  Pseudo  Code     1.Plot(dataset)      while(graph  is  non-­‐staKonary  =  True)      {smoothen  graph  to  make  it  staKonary}       2.  ACF/PACF(StaKonary  Graph)     3.  EsKmate  all  possible  model  parameters     4.  Calculate  AIC  values  of  all  model  parameters       5.  plot  (residual  of  model  parameters)    if(residual  graph  with  no  lag)      {Forecast  Dataset  with  these  parameters}    else  choose  other  esKmated  model  parameters  and  repeat  step  3       SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      5  
  • 6. Forecas5ng  Result         SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      6  
  • 7. Comparing  Arima  with  other  techniques   SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      7  
  • 8. Forecast  Accuracy  Results SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      8   METHOD   Mean     error   Root  mean     square     error   Mean     absolute     error   Mean     absolute     scaled  error   Mean   9.128060   756.3431   619.3957   1.739531   Naive   11.2086   495.6456   356.0705   1.000000   Drie   -­‐2.002087   496.345   358.0791   1.005641   Arima   6.649148   324.172   243.8181   0.7016939  
  • 9. Conclusions   Arima  Algorithm:   •   Arima  technique  is  more  accurate  than  tradiKonal  forecasKng  techniques.   •  PracKcal  and  useful.     LimitaKon:   •  Require  historical  data  –  the  larger  the  dataset,  the  be^er  the  forecast     ApplicaKon:     •  Manufacturing  Industry.   •  Sales  department.     •  Finance  Department.   SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      9  
  • 10. Appendix     Source  Code:     For  non-­‐seasonal  dataset     Arima  (p,  d,  q)  where  p,  d,  q  are  model  parameters     For  Seasonal  Dataset     Arima  (p,  d,  q)  (P,  D,  Q)  where  p,  d,  q  are  non  seasonal  parameters  and  P,  D,  Q  are  seasonal  parameters                    SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      10  
  • 11. Appendix   Arima  Forecas5ng  in  R     library(forecast)     library(fpp)      #forecas5ng     plot(sunspotarea,  main=  "  Original  Dataset")     sunspotarea1=diff(sunspotarea)     plot(sunspotarea1)     acf(sunspotarea1)     acf(sunspotarea1,  plot=FALSE)     pacf(sunspotarea1)     pacf(sunspotarea1,  plot=FALSE)     fit<-­‐Arima(sunspotarea,  order=c(2,1,5))     tsdisplay(residuals(fit))   plot(forecast(fit,  h=25),  main="ARIMA   FORECASTING",  xlab="Kme",  ylab="sunspotarea")     #Accuracy  checking     sun  <-­‐  window(sunspotarea,  end=2000)     plot(sun,  xlim=c(1874,2015))     lines(meanf(sun,h=15)$mean,  col=4)     lines(rwf(sun,h=15)$mean,  col=2)     lines(rwf(sun,drie=TRUE,h=15)$mean,  col=3)     legend("toplee",  lty=1,  col=c(4,2,3),                   legend=c("Mean  method","Naive  method","Drie   method"))     lines(sunspotarea)        SERA/NORA/PUNEET        CS6212/ARORA/FALL  2015      11  
  • 12. Thank  you     SERA/NORA/PUNEET                                                                    CS6212/ARORA/FALL                                                                                                                                                                  12