SlideShare a Scribd company logo
Toward Automatic Time-Series Forecasting Using
Neural Networks - Weixhong Yan
Presenter: Sean Golliher
1 / 19
Relationship to Research
Currently analyzing the performance of NEAT for Time Series
Forecasting (TSF)
Paper summarizes common approaches, and issues, using ANNs for
TSF
2 / 19
Claims of the Paper
Develops an automatic TSF model using a Generalized Regression
Neural Network (GRNN)
Shows promising results by winning NN3 time-series competition
against 60 different models
3 / 19
General Problems with ANN
Most approaches are ad hoc meaning they do some type of
preprocessing of the data
Typically try different ANN architectures to see which one performs
better
Nelson et al. : ANN inconsistency on TSF is the result of different
preprocessing strategies
Balkin et al. : ANNs require larger number of samples to be trained.
Real-world examples, financial etc., are short training samples.
4 / 19
RBF
RBF can be viewed as local linear regression model
Apply Gaussian kernel to input data. All inputs go to node of form:
G(x) = exp
−x − c
σ2
(1)
Find center points by assigning c (center point) to each point in data
set (measuring the distance to center point).
This is equivalent to doing a local regression (sigma affects the
smoothing of the approximation).
Output layer (the weights) are trained using least-squares regression
5 / 19
Generalized Definition for Regression
Computation of most probable value of Y for each value of X based
on finite number of possibly noisy measurements of X
Conditional mean of y given X (regression of y on X ) is given by:
E[y|X] =
∞
−∞
yf (X, y)dy
∞
−∞
f (X, y)dy
(2)
Since we don’t typically know the density function f(X, y) it can be
estimated using a Parzen window density estimator.
6 / 19
Generalized Definition for Regression
The generalized definition yields the following regression function:
ˆY (X) =
n
i=1
Y i exp −
D2
i
2σ2
n
i=1
exp −
D2
i
2σ2
(3)
Where D2
i = (X − Xi
)T (X − Xi
)
In the case of GRNN X is the input data and Xi
are the centers.
7 / 19
GRNN
G(x, xi ) are the standard radial basis functions
wi is the generalized regression equation
The spread factor dictates the performance
8 / 19
Claimed Benefits of GRNN
Easy to train
Can accurately approximate functions from sparse and noisy data
Note: Recent paper, Ahmed et al., claim GRNN inferior to MLP for
TSF
9 / 19
Methodology Requirements
Minimal human intervention
Computationally efficient for a large number of series
Good forecasting over range of data sets
10 / 19
Preprocessing: Outliers
Real-world time series has outliers
Outliers identified by
|x| ≥ 4max(|ma|, |mb|) (4)
where ma = median(xi−3, xi−2, xi−1) and
mb = median(xi+1, xi+2, xi+3)
If x is an outlier the value is replaced with average value of two points
before and after x
11 / 19
Preprocessing: Trends
Real-world time series has trends. Could be due to seasonality or other
factors.
Common approaches are curve fitting, filtering, and differencing.
Identifying trends is difficult to do algorithmically
Proposes detrending scheme:
Split series into segments. If monthly split into 12 if quarterly split into
4
Mean of historical observations within each segment is subtracted from
every historical observation in segment.
If x is an outlier the value is replaced with average value of two points
before and after x
12 / 19
Preprocessing: Seasonality
Identifying seasonality is typically a manual process
Author used a simple approach and defined short series as n ≤ 60 and
long n ≥ 60
Uses autocorrelation coefficients at one and two seasonal lags to
decide if seasonal
Uses a standard method for subtracting out seasonality from series
data
13 / 19
ANN Modeling
Aspects of ANN modeling
Spread Factor. Typically found empirically since no good analytic
approach has been found. Some guidance was given by Haykin
σ = dmax√
2n
where dmax is max distance between the training points.
Proposes spread factor be set to d50, d75, d95 (percentiles) of the
nearest distance of all training samples to rest of points.
Uses three GRNNs that all take the same input and are combined to
give the final output.
Choice of combining three GRNNs is based on previous success in
literature
14 / 19
ANN Modeling Cont’d
Input selection is considered one of the most important aspects in
TSF
Two general approaches: filter and wrapper
Filtering selects features based on data itself (independent of learning
algorithm)
Wrapping approaches use the learning algorithm. Wrapper typically
performs better.
Author uses contiguous lag and limits to one full season for 12 month
data.
15 / 19
Experimental Results
Use NN3 time-series competition dataset which has composed of
Dataset A and Dataset B
Dataset A is 111 monthly time series data drawn from empirical
business time series
Dataset B is a small subset of Dataset A which consists of 11 time
series
Error is measured using sMAPE
16 / 19
Experimental Results
B indicates statistical model and C indicates computational
intelligence model
17 / 19
Ablation Studies
SP: Spread, MSA: Multiple Step Ahead
18 / 19
Discussion
Are TSF competitions just a demonstration of the no free lunch
theorem? Why is the theorem not mentioned?
Did he prove his approach was “better” or did this approach just
outperform on a particular contest?
Why doesn’t the training of the GRNN factor out outliers and
seasonality on its own? Isn’t that what training is for?
Why did he choose a GRNN? Previous papers said they perform
poorly.
What kind of bias does the detrending scheme introduce?
Paper was “rule of thumb” oriented. Is there a way to make an
automatic approach more rigorous?
19 / 19

More Related Content

What's hot

Khurram
KhurramKhurram
Khurram
JJkedst
 
Ruta solucion de problemas
Ruta solucion de problemasRuta solucion de problemas
Ruta solucion de problemas
Luz Zoraida Hernández Vera
 
Atlason et al, 2003 WSC_Subgradient Approximation
Atlason et al, 2003 WSC_Subgradient ApproximationAtlason et al, 2003 WSC_Subgradient Approximation
Atlason et al, 2003 WSC_Subgradient ApproximationMichael Beyer
 
Interpolation and-its-application
Interpolation and-its-applicationInterpolation and-its-application
Interpolation and-its-application
Apurbo Datta
 
Size measurement and estimation
Size measurement and estimationSize measurement and estimation
Size measurement and estimation
Louis A. Poulin
 
Software of Time Series Forecasting based on Combinations of Fuzzy and Statis...
Software of Time Series Forecasting based on Combinations of Fuzzy and Statis...Software of Time Series Forecasting based on Combinations of Fuzzy and Statis...
Software of Time Series Forecasting based on Combinations of Fuzzy and Statis...
ITIIIndustries
 
07 dimensionality reduction
07 dimensionality reduction07 dimensionality reduction
07 dimensionality reduction
Marco Quartulli
 
Mann Whitney U Test | Statistics
Mann Whitney U Test | StatisticsMann Whitney U Test | Statistics
Mann Whitney U Test | Statistics
Transweb Global Inc
 
Six sigma
Six sigma Six sigma
Principal Component Analysis and Clustering
Principal Component Analysis and ClusteringPrincipal Component Analysis and Clustering
Principal Component Analysis and Clustering
Usha Vijay
 
Graph Based Pattern Recognition
Graph Based Pattern RecognitionGraph Based Pattern Recognition
Graph Based Pattern Recognition
Nicola Strisciuglio
 
Week 4 forecasting - time series - smoothing and decomposition - m.awaluddin.t
Week 4   forecasting - time series - smoothing and decomposition - m.awaluddin.tWeek 4   forecasting - time series - smoothing and decomposition - m.awaluddin.t
Week 4 forecasting - time series - smoothing and decomposition - m.awaluddin.t
Maling Senk
 
Minimization of Assignment Problems
Minimization of Assignment ProblemsMinimization of Assignment Problems
Minimization of Assignment Problems
ijtsrd
 
Chap011
Chap011Chap011
2 way anova
2 way anova2 way anova
2 way anova
akash dalvi
 
GRADIENT OMISSIVE DESCENT IS A MINIMIZATION ALGORITHM
GRADIENT OMISSIVE DESCENT IS A MINIMIZATION ALGORITHMGRADIENT OMISSIVE DESCENT IS A MINIMIZATION ALGORITHM
GRADIENT OMISSIVE DESCENT IS A MINIMIZATION ALGORITHM
ijscai
 
Grouped time-series forecasting: Application to regional infant mortality counts
Grouped time-series forecasting: Application to regional infant mortality countsGrouped time-series forecasting: Application to regional infant mortality counts
Grouped time-series forecasting: Application to regional infant mortality countshanshang
 
Zena MWU
Zena MWUZena MWU
Zena MWU
JJkedst
 
Principal Component Analysis
Principal Component AnalysisPrincipal Component Analysis
Principal Component Analysis
Ricardo Wendell Rodrigues da Silveira
 

What's hot (19)

Khurram
KhurramKhurram
Khurram
 
Ruta solucion de problemas
Ruta solucion de problemasRuta solucion de problemas
Ruta solucion de problemas
 
Atlason et al, 2003 WSC_Subgradient Approximation
Atlason et al, 2003 WSC_Subgradient ApproximationAtlason et al, 2003 WSC_Subgradient Approximation
Atlason et al, 2003 WSC_Subgradient Approximation
 
Interpolation and-its-application
Interpolation and-its-applicationInterpolation and-its-application
Interpolation and-its-application
 
Size measurement and estimation
Size measurement and estimationSize measurement and estimation
Size measurement and estimation
 
Software of Time Series Forecasting based on Combinations of Fuzzy and Statis...
Software of Time Series Forecasting based on Combinations of Fuzzy and Statis...Software of Time Series Forecasting based on Combinations of Fuzzy and Statis...
Software of Time Series Forecasting based on Combinations of Fuzzy and Statis...
 
07 dimensionality reduction
07 dimensionality reduction07 dimensionality reduction
07 dimensionality reduction
 
Mann Whitney U Test | Statistics
Mann Whitney U Test | StatisticsMann Whitney U Test | Statistics
Mann Whitney U Test | Statistics
 
Six sigma
Six sigma Six sigma
Six sigma
 
Principal Component Analysis and Clustering
Principal Component Analysis and ClusteringPrincipal Component Analysis and Clustering
Principal Component Analysis and Clustering
 
Graph Based Pattern Recognition
Graph Based Pattern RecognitionGraph Based Pattern Recognition
Graph Based Pattern Recognition
 
Week 4 forecasting - time series - smoothing and decomposition - m.awaluddin.t
Week 4   forecasting - time series - smoothing and decomposition - m.awaluddin.tWeek 4   forecasting - time series - smoothing and decomposition - m.awaluddin.t
Week 4 forecasting - time series - smoothing and decomposition - m.awaluddin.t
 
Minimization of Assignment Problems
Minimization of Assignment ProblemsMinimization of Assignment Problems
Minimization of Assignment Problems
 
Chap011
Chap011Chap011
Chap011
 
2 way anova
2 way anova2 way anova
2 way anova
 
GRADIENT OMISSIVE DESCENT IS A MINIMIZATION ALGORITHM
GRADIENT OMISSIVE DESCENT IS A MINIMIZATION ALGORITHMGRADIENT OMISSIVE DESCENT IS A MINIMIZATION ALGORITHM
GRADIENT OMISSIVE DESCENT IS A MINIMIZATION ALGORITHM
 
Grouped time-series forecasting: Application to regional infant mortality counts
Grouped time-series forecasting: Application to regional infant mortality countsGrouped time-series forecasting: Application to regional infant mortality counts
Grouped time-series forecasting: Application to regional infant mortality counts
 
Zena MWU
Zena MWUZena MWU
Zena MWU
 
Principal Component Analysis
Principal Component AnalysisPrincipal Component Analysis
Principal Component Analysis
 

Viewers also liked

Adaptive short term forecasting
Adaptive short term forecastingAdaptive short term forecasting
Adaptive short term forecasting
Alex
 
Analyzing and forecasting time series data ppt @ bec doms
Analyzing and forecasting time series data ppt @ bec domsAnalyzing and forecasting time series data ppt @ bec doms
Analyzing and forecasting time series data ppt @ bec doms
Babasab Patil
 
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
 
Chap19 time series-analysis_and_forecasting
Chap19 time series-analysis_and_forecastingChap19 time series-analysis_and_forecasting
Chap19 time series-analysis_and_forecastingVishal Kukreja
 
Time series Forecasting
Time series ForecastingTime series Forecasting
Time series Forecasting
haroonrashidlone
 
Chap15 time series forecasting & index number
Chap15 time series forecasting & index numberChap15 time series forecasting & index number
Chap15 time series forecasting & index number
Uni Azza Aunillah
 
Chapter 16
Chapter 16Chapter 16
Chapter 16bmcfad01
 
Demand forecasting by time series analysis
Demand forecasting by time series analysisDemand forecasting by time series analysis
Demand forecasting by time series analysis
Sunny Gandhi
 
Time Series
Time SeriesTime Series
Time Seriesyush313
 
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
Derek Kane
 

Viewers also liked (10)

Adaptive short term forecasting
Adaptive short term forecastingAdaptive short term forecasting
Adaptive short term forecasting
 
Analyzing and forecasting time series data ppt @ bec doms
Analyzing and forecasting time series data ppt @ bec domsAnalyzing and forecasting time series data ppt @ bec doms
Analyzing and forecasting time series data ppt @ bec doms
 
Automatic algorithms for time series forecasting
Automatic algorithms for time series forecastingAutomatic algorithms for time series forecasting
Automatic algorithms for time series forecasting
 
Chap19 time series-analysis_and_forecasting
Chap19 time series-analysis_and_forecastingChap19 time series-analysis_and_forecasting
Chap19 time series-analysis_and_forecasting
 
Time series Forecasting
Time series ForecastingTime series Forecasting
Time series Forecasting
 
Chap15 time series forecasting & index number
Chap15 time series forecasting & index numberChap15 time series forecasting & index number
Chap15 time series forecasting & index number
 
Chapter 16
Chapter 16Chapter 16
Chapter 16
 
Demand forecasting by time series analysis
Demand forecasting by time series analysisDemand forecasting by time series analysis
Demand forecasting by time series analysis
 
Time Series
Time SeriesTime Series
Time Series
 
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
 

Similar to Time Series Forecasting using Neural Nets (GNNNs)

MULTI-OBJECTIVE ENERGY EFFICIENT OPTIMIZATION ALGORITHM FOR COVERAGE CONTROL ...
MULTI-OBJECTIVE ENERGY EFFICIENT OPTIMIZATION ALGORITHM FOR COVERAGE CONTROL ...MULTI-OBJECTIVE ENERGY EFFICIENT OPTIMIZATION ALGORITHM FOR COVERAGE CONTROL ...
MULTI-OBJECTIVE ENERGY EFFICIENT OPTIMIZATION ALGORITHM FOR COVERAGE CONTROL ...
ijcseit
 
Particle filter
Particle filterParticle filter
Particle filter
Mohammad Reza Jabbari
 
CLIM Fall 2017 Course: Statistics for Climate Research, Climate Informatics -...
CLIM Fall 2017 Course: Statistics for Climate Research, Climate Informatics -...CLIM Fall 2017 Course: Statistics for Climate Research, Climate Informatics -...
CLIM Fall 2017 Course: Statistics for Climate Research, Climate Informatics -...
The Statistical and Applied Mathematical Sciences Institute
 
Lesson 6 measures of central tendency
Lesson 6 measures of central tendencyLesson 6 measures of central tendency
Lesson 6 measures of central tendencynurun2010
 
CPSC 531: System Modeling and Simulation.pptx
CPSC 531:System Modeling and Simulation.pptxCPSC 531:System Modeling and Simulation.pptx
CPSC 531: System Modeling and Simulation.pptx
Farhan27013
 
A Mathematical Programming Approach for Selection of Variables in Cluster Ana...
A Mathematical Programming Approach for Selection of Variables in Cluster Ana...A Mathematical Programming Approach for Selection of Variables in Cluster Ana...
A Mathematical Programming Approach for Selection of Variables in Cluster Ana...
IJRES Journal
 
Estimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample SetsEstimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample Sets
Förderverein Technische Fakultät
 
Nonnegative Matrix Factorization with Side Information for Time Series Recove...
Nonnegative Matrix Factorization with Side Information for Time Series Recove...Nonnegative Matrix Factorization with Side Information for Time Series Recove...
Nonnegative Matrix Factorization with Side Information for Time Series Recove...
Paris Women in Machine Learning and Data Science
 
A Fast Multi-objective Evolutionary Approach for Designing Large-Scale Optica...
A Fast Multi-objective Evolutionary Approach for Designing Large-Scale Optica...A Fast Multi-objective Evolutionary Approach for Designing Large-Scale Optica...
A Fast Multi-objective Evolutionary Approach for Designing Large-Scale Optica...
Annibale Panichella
 
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
IJITCA Journal
 
IRJET- Supervised Learning Classification Algorithms Comparison
IRJET- Supervised Learning Classification Algorithms ComparisonIRJET- Supervised Learning Classification Algorithms Comparison
IRJET- Supervised Learning Classification Algorithms Comparison
IRJET Journal
 
IRJET- Supervised Learning Classification Algorithms Comparison
IRJET- Supervised Learning Classification Algorithms ComparisonIRJET- Supervised Learning Classification Algorithms Comparison
IRJET- Supervised Learning Classification Algorithms Comparison
IRJET Journal
 
Wasserstein 1031 thesis [Chung il kim]
Wasserstein 1031 thesis [Chung il kim]Wasserstein 1031 thesis [Chung il kim]
Wasserstein 1031 thesis [Chung il kim]
Chung-Il Kim
 
Distributed Streams
Distributed StreamsDistributed Streams
Distributed Streams
Ashraf Bashir
 
Investigating the 3D structure of the genome with Hi-C data analysis
Investigating the 3D structure of the genome with Hi-C data analysisInvestigating the 3D structure of the genome with Hi-C data analysis
Investigating the 3D structure of the genome with Hi-C data analysis
tuxette
 
A NEW ALGORITHM FOR SOLVING FULLY FUZZY BI-LEVEL QUADRATIC PROGRAMMING PROBLEMS
A NEW ALGORITHM FOR SOLVING FULLY FUZZY BI-LEVEL QUADRATIC PROGRAMMING PROBLEMSA NEW ALGORITHM FOR SOLVING FULLY FUZZY BI-LEVEL QUADRATIC PROGRAMMING PROBLEMS
A NEW ALGORITHM FOR SOLVING FULLY FUZZY BI-LEVEL QUADRATIC PROGRAMMING PROBLEMS
orajjournal
 
Comparison of Cost Estimation Methods using Hybrid Artificial Intelligence on...
Comparison of Cost Estimation Methods using Hybrid Artificial Intelligence on...Comparison of Cost Estimation Methods using Hybrid Artificial Intelligence on...
Comparison of Cost Estimation Methods using Hybrid Artificial Intelligence on...
IJERA Editor
 

Similar to Time Series Forecasting using Neural Nets (GNNNs) (20)

Ankit presentation
Ankit presentationAnkit presentation
Ankit presentation
 
MULTI-OBJECTIVE ENERGY EFFICIENT OPTIMIZATION ALGORITHM FOR COVERAGE CONTROL ...
MULTI-OBJECTIVE ENERGY EFFICIENT OPTIMIZATION ALGORITHM FOR COVERAGE CONTROL ...MULTI-OBJECTIVE ENERGY EFFICIENT OPTIMIZATION ALGORITHM FOR COVERAGE CONTROL ...
MULTI-OBJECTIVE ENERGY EFFICIENT OPTIMIZATION ALGORITHM FOR COVERAGE CONTROL ...
 
Particle filter
Particle filterParticle filter
Particle filter
 
CLIM Fall 2017 Course: Statistics for Climate Research, Climate Informatics -...
CLIM Fall 2017 Course: Statistics for Climate Research, Climate Informatics -...CLIM Fall 2017 Course: Statistics for Climate Research, Climate Informatics -...
CLIM Fall 2017 Course: Statistics for Climate Research, Climate Informatics -...
 
Lesson 6 measures of central tendency
Lesson 6 measures of central tendencyLesson 6 measures of central tendency
Lesson 6 measures of central tendency
 
CPSC 531: System Modeling and Simulation.pptx
CPSC 531:System Modeling and Simulation.pptxCPSC 531:System Modeling and Simulation.pptx
CPSC 531: System Modeling and Simulation.pptx
 
A Mathematical Programming Approach for Selection of Variables in Cluster Ana...
A Mathematical Programming Approach for Selection of Variables in Cluster Ana...A Mathematical Programming Approach for Selection of Variables in Cluster Ana...
A Mathematical Programming Approach for Selection of Variables in Cluster Ana...
 
Estimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample SetsEstimating Space-Time Covariance from Finite Sample Sets
Estimating Space-Time Covariance from Finite Sample Sets
 
Nonnegative Matrix Factorization with Side Information for Time Series Recove...
Nonnegative Matrix Factorization with Side Information for Time Series Recove...Nonnegative Matrix Factorization with Side Information for Time Series Recove...
Nonnegative Matrix Factorization with Side Information for Time Series Recove...
 
A Fast Multi-objective Evolutionary Approach for Designing Large-Scale Optica...
A Fast Multi-objective Evolutionary Approach for Designing Large-Scale Optica...A Fast Multi-objective Evolutionary Approach for Designing Large-Scale Optica...
A Fast Multi-objective Evolutionary Approach for Designing Large-Scale Optica...
 
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
APPLYING DYNAMIC MODEL FOR MULTIPLE MANOEUVRING TARGET TRACKING USING PARTICL...
 
ppt0320defenseday
ppt0320defensedayppt0320defenseday
ppt0320defenseday
 
AROPUB-IJPGE-14-30
AROPUB-IJPGE-14-30AROPUB-IJPGE-14-30
AROPUB-IJPGE-14-30
 
IRJET- Supervised Learning Classification Algorithms Comparison
IRJET- Supervised Learning Classification Algorithms ComparisonIRJET- Supervised Learning Classification Algorithms Comparison
IRJET- Supervised Learning Classification Algorithms Comparison
 
IRJET- Supervised Learning Classification Algorithms Comparison
IRJET- Supervised Learning Classification Algorithms ComparisonIRJET- Supervised Learning Classification Algorithms Comparison
IRJET- Supervised Learning Classification Algorithms Comparison
 
Wasserstein 1031 thesis [Chung il kim]
Wasserstein 1031 thesis [Chung il kim]Wasserstein 1031 thesis [Chung il kim]
Wasserstein 1031 thesis [Chung il kim]
 
Distributed Streams
Distributed StreamsDistributed Streams
Distributed Streams
 
Investigating the 3D structure of the genome with Hi-C data analysis
Investigating the 3D structure of the genome with Hi-C data analysisInvestigating the 3D structure of the genome with Hi-C data analysis
Investigating the 3D structure of the genome with Hi-C data analysis
 
A NEW ALGORITHM FOR SOLVING FULLY FUZZY BI-LEVEL QUADRATIC PROGRAMMING PROBLEMS
A NEW ALGORITHM FOR SOLVING FULLY FUZZY BI-LEVEL QUADRATIC PROGRAMMING PROBLEMSA NEW ALGORITHM FOR SOLVING FULLY FUZZY BI-LEVEL QUADRATIC PROGRAMMING PROBLEMS
A NEW ALGORITHM FOR SOLVING FULLY FUZZY BI-LEVEL QUADRATIC PROGRAMMING PROBLEMS
 
Comparison of Cost Estimation Methods using Hybrid Artificial Intelligence on...
Comparison of Cost Estimation Methods using Hybrid Artificial Intelligence on...Comparison of Cost Estimation Methods using Hybrid Artificial Intelligence on...
Comparison of Cost Estimation Methods using Hybrid Artificial Intelligence on...
 

More from Sean Golliher

A Unifying Probabilistic Perspective for Spectral Dimensionality Reduction:
A Unifying Probabilistic Perspective for Spectral Dimensionality Reduction:A Unifying Probabilistic Perspective for Spectral Dimensionality Reduction:
A Unifying Probabilistic Perspective for Spectral Dimensionality Reduction:Sean Golliher
 
Property Matching and Query Expansion on Linked Data Using Kullback-Leibler D...
Property Matching and Query Expansion on Linked Data Using Kullback-Leibler D...Property Matching and Query Expansion on Linked Data Using Kullback-Leibler D...
Property Matching and Query Expansion on Linked Data Using Kullback-Leibler D...
Sean Golliher
 
Lecture 9 - Machine Learning and Support Vector Machines (SVM)
Lecture 9 - Machine Learning and Support Vector Machines (SVM)Lecture 9 - Machine Learning and Support Vector Machines (SVM)
Lecture 9 - Machine Learning and Support Vector Machines (SVM)
Sean Golliher
 
Probabilistic Retrieval Models - Sean Golliher Lecture 8 MSU CSCI 494
Probabilistic Retrieval Models - Sean Golliher Lecture 8 MSU CSCI 494Probabilistic Retrieval Models - Sean Golliher Lecture 8 MSU CSCI 494
Probabilistic Retrieval Models - Sean Golliher Lecture 8 MSU CSCI 494
Sean Golliher
 
Lecture 7- Text Statistics and Document Parsing
Lecture 7- Text Statistics and Document ParsingLecture 7- Text Statistics and Document Parsing
Lecture 7- Text Statistics and Document Parsing
Sean Golliher
 
Information Retrieval, Encoding, Indexing, Big Table. Lecture 6 - Indexing
Information Retrieval, Encoding, Indexing, Big Table. Lecture 6  - IndexingInformation Retrieval, Encoding, Indexing, Big Table. Lecture 6  - Indexing
Information Retrieval, Encoding, Indexing, Big Table. Lecture 6 - Indexing
Sean Golliher
 
PageRank and The Google Matrix
PageRank and The Google MatrixPageRank and The Google Matrix
PageRank and The Google Matrix
Sean Golliher
 
CSCI 494 - Lect. 3. Anatomy of Search Engines/Building a Crawler
CSCI 494 - Lect. 3. Anatomy of Search Engines/Building a CrawlerCSCI 494 - Lect. 3. Anatomy of Search Engines/Building a Crawler
CSCI 494 - Lect. 3. Anatomy of Search Engines/Building a Crawler
Sean Golliher
 

More from Sean Golliher (9)

A Unifying Probabilistic Perspective for Spectral Dimensionality Reduction:
A Unifying Probabilistic Perspective for Spectral Dimensionality Reduction:A Unifying Probabilistic Perspective for Spectral Dimensionality Reduction:
A Unifying Probabilistic Perspective for Spectral Dimensionality Reduction:
 
Goprez sg
Goprez  sgGoprez  sg
Goprez sg
 
Property Matching and Query Expansion on Linked Data Using Kullback-Leibler D...
Property Matching and Query Expansion on Linked Data Using Kullback-Leibler D...Property Matching and Query Expansion on Linked Data Using Kullback-Leibler D...
Property Matching and Query Expansion on Linked Data Using Kullback-Leibler D...
 
Lecture 9 - Machine Learning and Support Vector Machines (SVM)
Lecture 9 - Machine Learning and Support Vector Machines (SVM)Lecture 9 - Machine Learning and Support Vector Machines (SVM)
Lecture 9 - Machine Learning and Support Vector Machines (SVM)
 
Probabilistic Retrieval Models - Sean Golliher Lecture 8 MSU CSCI 494
Probabilistic Retrieval Models - Sean Golliher Lecture 8 MSU CSCI 494Probabilistic Retrieval Models - Sean Golliher Lecture 8 MSU CSCI 494
Probabilistic Retrieval Models - Sean Golliher Lecture 8 MSU CSCI 494
 
Lecture 7- Text Statistics and Document Parsing
Lecture 7- Text Statistics and Document ParsingLecture 7- Text Statistics and Document Parsing
Lecture 7- Text Statistics and Document Parsing
 
Information Retrieval, Encoding, Indexing, Big Table. Lecture 6 - Indexing
Information Retrieval, Encoding, Indexing, Big Table. Lecture 6  - IndexingInformation Retrieval, Encoding, Indexing, Big Table. Lecture 6  - Indexing
Information Retrieval, Encoding, Indexing, Big Table. Lecture 6 - Indexing
 
PageRank and The Google Matrix
PageRank and The Google MatrixPageRank and The Google Matrix
PageRank and The Google Matrix
 
CSCI 494 - Lect. 3. Anatomy of Search Engines/Building a Crawler
CSCI 494 - Lect. 3. Anatomy of Search Engines/Building a CrawlerCSCI 494 - Lect. 3. Anatomy of Search Engines/Building a Crawler
CSCI 494 - Lect. 3. Anatomy of Search Engines/Building a Crawler
 

Recently uploaded

Nutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technologyNutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technology
Lokesh Patil
 
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCINGRNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
AADYARAJPANDEY1
 
platelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptxplatelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptx
muralinath2
 
Richard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlandsRichard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlands
Richard Gill
 
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
NathanBaughman3
 
Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...
Sérgio Sacani
 
Structures and textures of metamorphic rocks
Structures and textures of metamorphic rocksStructures and textures of metamorphic rocks
Structures and textures of metamorphic rocks
kumarmathi863
 
Hemostasis_importance& clinical significance.pptx
Hemostasis_importance& clinical significance.pptxHemostasis_importance& clinical significance.pptx
Hemostasis_importance& clinical significance.pptx
muralinath2
 
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptxBody fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
muralinath2
 
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
Sérgio Sacani
 
Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.
Nistarini College, Purulia (W.B) India
 
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of LipidsGBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
Areesha Ahmad
 
Unveiling the Energy Potential of Marshmallow Deposits.pdf
Unveiling the Energy Potential of Marshmallow Deposits.pdfUnveiling the Energy Potential of Marshmallow Deposits.pdf
Unveiling the Energy Potential of Marshmallow Deposits.pdf
Erdal Coalmaker
 
erythropoiesis-I_mechanism& clinical significance.pptx
erythropoiesis-I_mechanism& clinical significance.pptxerythropoiesis-I_mechanism& clinical significance.pptx
erythropoiesis-I_mechanism& clinical significance.pptx
muralinath2
 
EY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptxEY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptx
AlguinaldoKong
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
Columbia Weather Systems
 
general properties of oerganologametal.ppt
general properties of oerganologametal.pptgeneral properties of oerganologametal.ppt
general properties of oerganologametal.ppt
IqrimaNabilatulhusni
 
What is greenhouse gasses and how many gasses are there to affect the Earth.
What is greenhouse gasses and how many gasses are there to affect the Earth.What is greenhouse gasses and how many gasses are there to affect the Earth.
What is greenhouse gasses and how many gasses are there to affect the Earth.
moosaasad1975
 
NuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final versionNuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final version
pablovgd
 
Comparative structure of adrenal gland in vertebrates
Comparative structure of adrenal gland in vertebratesComparative structure of adrenal gland in vertebrates
Comparative structure of adrenal gland in vertebrates
sachin783648
 

Recently uploaded (20)

Nutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technologyNutraceutical market, scope and growth: Herbal drug technology
Nutraceutical market, scope and growth: Herbal drug technology
 
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCINGRNA INTERFERENCE: UNRAVELING GENETIC SILENCING
RNA INTERFERENCE: UNRAVELING GENETIC SILENCING
 
platelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptxplatelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptx
 
Richard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlandsRichard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlands
 
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
Astronomy Update- Curiosity’s exploration of Mars _ Local Briefs _ leadertele...
 
Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...Multi-source connectivity as the driver of solar wind variability in the heli...
Multi-source connectivity as the driver of solar wind variability in the heli...
 
Structures and textures of metamorphic rocks
Structures and textures of metamorphic rocksStructures and textures of metamorphic rocks
Structures and textures of metamorphic rocks
 
Hemostasis_importance& clinical significance.pptx
Hemostasis_importance& clinical significance.pptxHemostasis_importance& clinical significance.pptx
Hemostasis_importance& clinical significance.pptx
 
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptxBody fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
Body fluids_tonicity_dehydration_hypovolemia_hypervolemia.pptx
 
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
THE IMPORTANCE OF MARTIAN ATMOSPHERE SAMPLE RETURN.
 
Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.
 
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of LipidsGBSN - Biochemistry (Unit 5) Chemistry of Lipids
GBSN - Biochemistry (Unit 5) Chemistry of Lipids
 
Unveiling the Energy Potential of Marshmallow Deposits.pdf
Unveiling the Energy Potential of Marshmallow Deposits.pdfUnveiling the Energy Potential of Marshmallow Deposits.pdf
Unveiling the Energy Potential of Marshmallow Deposits.pdf
 
erythropoiesis-I_mechanism& clinical significance.pptx
erythropoiesis-I_mechanism& clinical significance.pptxerythropoiesis-I_mechanism& clinical significance.pptx
erythropoiesis-I_mechanism& clinical significance.pptx
 
EY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptxEY - Supply Chain Services 2018_template.pptx
EY - Supply Chain Services 2018_template.pptx
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
 
general properties of oerganologametal.ppt
general properties of oerganologametal.pptgeneral properties of oerganologametal.ppt
general properties of oerganologametal.ppt
 
What is greenhouse gasses and how many gasses are there to affect the Earth.
What is greenhouse gasses and how many gasses are there to affect the Earth.What is greenhouse gasses and how many gasses are there to affect the Earth.
What is greenhouse gasses and how many gasses are there to affect the Earth.
 
NuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final versionNuGOweek 2024 Ghent - programme - final version
NuGOweek 2024 Ghent - programme - final version
 
Comparative structure of adrenal gland in vertebrates
Comparative structure of adrenal gland in vertebratesComparative structure of adrenal gland in vertebrates
Comparative structure of adrenal gland in vertebrates
 

Time Series Forecasting using Neural Nets (GNNNs)

  • 1. Toward Automatic Time-Series Forecasting Using Neural Networks - Weixhong Yan Presenter: Sean Golliher 1 / 19
  • 2. Relationship to Research Currently analyzing the performance of NEAT for Time Series Forecasting (TSF) Paper summarizes common approaches, and issues, using ANNs for TSF 2 / 19
  • 3. Claims of the Paper Develops an automatic TSF model using a Generalized Regression Neural Network (GRNN) Shows promising results by winning NN3 time-series competition against 60 different models 3 / 19
  • 4. General Problems with ANN Most approaches are ad hoc meaning they do some type of preprocessing of the data Typically try different ANN architectures to see which one performs better Nelson et al. : ANN inconsistency on TSF is the result of different preprocessing strategies Balkin et al. : ANNs require larger number of samples to be trained. Real-world examples, financial etc., are short training samples. 4 / 19
  • 5. RBF RBF can be viewed as local linear regression model Apply Gaussian kernel to input data. All inputs go to node of form: G(x) = exp −x − c σ2 (1) Find center points by assigning c (center point) to each point in data set (measuring the distance to center point). This is equivalent to doing a local regression (sigma affects the smoothing of the approximation). Output layer (the weights) are trained using least-squares regression 5 / 19
  • 6. Generalized Definition for Regression Computation of most probable value of Y for each value of X based on finite number of possibly noisy measurements of X Conditional mean of y given X (regression of y on X ) is given by: E[y|X] = ∞ −∞ yf (X, y)dy ∞ −∞ f (X, y)dy (2) Since we don’t typically know the density function f(X, y) it can be estimated using a Parzen window density estimator. 6 / 19
  • 7. Generalized Definition for Regression The generalized definition yields the following regression function: ˆY (X) = n i=1 Y i exp − D2 i 2σ2 n i=1 exp − D2 i 2σ2 (3) Where D2 i = (X − Xi )T (X − Xi ) In the case of GRNN X is the input data and Xi are the centers. 7 / 19
  • 8. GRNN G(x, xi ) are the standard radial basis functions wi is the generalized regression equation The spread factor dictates the performance 8 / 19
  • 9. Claimed Benefits of GRNN Easy to train Can accurately approximate functions from sparse and noisy data Note: Recent paper, Ahmed et al., claim GRNN inferior to MLP for TSF 9 / 19
  • 10. Methodology Requirements Minimal human intervention Computationally efficient for a large number of series Good forecasting over range of data sets 10 / 19
  • 11. Preprocessing: Outliers Real-world time series has outliers Outliers identified by |x| ≥ 4max(|ma|, |mb|) (4) where ma = median(xi−3, xi−2, xi−1) and mb = median(xi+1, xi+2, xi+3) If x is an outlier the value is replaced with average value of two points before and after x 11 / 19
  • 12. Preprocessing: Trends Real-world time series has trends. Could be due to seasonality or other factors. Common approaches are curve fitting, filtering, and differencing. Identifying trends is difficult to do algorithmically Proposes detrending scheme: Split series into segments. If monthly split into 12 if quarterly split into 4 Mean of historical observations within each segment is subtracted from every historical observation in segment. If x is an outlier the value is replaced with average value of two points before and after x 12 / 19
  • 13. Preprocessing: Seasonality Identifying seasonality is typically a manual process Author used a simple approach and defined short series as n ≤ 60 and long n ≥ 60 Uses autocorrelation coefficients at one and two seasonal lags to decide if seasonal Uses a standard method for subtracting out seasonality from series data 13 / 19
  • 14. ANN Modeling Aspects of ANN modeling Spread Factor. Typically found empirically since no good analytic approach has been found. Some guidance was given by Haykin σ = dmax√ 2n where dmax is max distance between the training points. Proposes spread factor be set to d50, d75, d95 (percentiles) of the nearest distance of all training samples to rest of points. Uses three GRNNs that all take the same input and are combined to give the final output. Choice of combining three GRNNs is based on previous success in literature 14 / 19
  • 15. ANN Modeling Cont’d Input selection is considered one of the most important aspects in TSF Two general approaches: filter and wrapper Filtering selects features based on data itself (independent of learning algorithm) Wrapping approaches use the learning algorithm. Wrapper typically performs better. Author uses contiguous lag and limits to one full season for 12 month data. 15 / 19
  • 16. Experimental Results Use NN3 time-series competition dataset which has composed of Dataset A and Dataset B Dataset A is 111 monthly time series data drawn from empirical business time series Dataset B is a small subset of Dataset A which consists of 11 time series Error is measured using sMAPE 16 / 19
  • 17. Experimental Results B indicates statistical model and C indicates computational intelligence model 17 / 19
  • 18. Ablation Studies SP: Spread, MSA: Multiple Step Ahead 18 / 19
  • 19. Discussion Are TSF competitions just a demonstration of the no free lunch theorem? Why is the theorem not mentioned? Did he prove his approach was “better” or did this approach just outperform on a particular contest? Why doesn’t the training of the GRNN factor out outliers and seasonality on its own? Isn’t that what training is for? Why did he choose a GRNN? Previous papers said they perform poorly. What kind of bias does the detrending scheme introduce? Paper was “rule of thumb” oriented. Is there a way to make an automatic approach more rigorous? 19 / 19