SlideShare a Scribd company logo
Affine www.affinenalytics.com
AFFINE BLOG
Affine www.affinenalytics.com
Affine Blog
New Product Forecasting using Deep Learning
Background
Forecasting demand for new product launches has been a major challenge for industries and cost of error has been high. Under predict demand
and you lose on potential sales, overpredict them and there is excess inventory to take care of. Multiple research suggests that new product
contributes to one-third of the organization sales across the various industry. Industries like Apparel Retailer or Gaming thrive on new launches
and innovation, and this number can easily inflate to as high as 70%. Hence accuracy of demand forecasts has been a top priority for marketers and
inventory planning teams.
There are a whole lot of analytics techniques adopted by analysts and decision scientists to better forecast potential demand, the popular ones
being:
- Market Test Methods – Delphi/Survey based exercise
- Diffusion modeling
- Conjoint & Regression based look alike models
While Market Test Methods are still popular but they need a lot of domain expertise and cost intensive processes to drive desired results. In recent
times, techniques like Conjoint and Regression based methods are more frequently leveraged by marketers and data scientists. A typical demand
forecasting process for the same is highlighted below:
Though the process implements an analytical temper of quantifying cross synergies between business drivers and is scalable enough to generate
dynamic business scenarios on the go, it falls short of expectations on following two aspects
It includes heuristics exercise of identifying analogous products by manually defining product similarity. Besides, the robustness of this exercise is
influenced by domain expertise. The manual process coupled with subjectivity of the process might lead to questionable accuracy standards
It is still a supervised model and the key demand drivers need manual tuning to generate better forecasting accuracy
For retailers and manufacturers esp. apparel, food, etc. where the rate of innovation is high and assortments keep refreshing from season to season,
a heuristic method would lead to high cost and error for any demand forecasting exercise.`
Since the primary reason of including product features in demand forecasting model is to under-
stand cognitive influence on customer purchase behavior, a deep learning framework is a better
and accurate approach to capture the same
Case Background
An apparel retailer wanted to forecast demand for its newly launched “Footwear” styles across various lifecycle stages. The current forecasting
engine implemented various supervised techniques which were ensemble to generate desired demand forecasting. It had 2 major shortcomings:
- The analogous product selection mechanism was heuristic and lead to low accuracy level in downstream processes
- The heuristic exercise was a significant road block in evolving the current process to a scalable architecture, making the overall experience a
cost intensive one
- The engine was not able to replicate the product life cycle accurately
Proposed Solution
We proposed to tackle the problem through an intelligent, automated and scalable framework
- Leverage Convoluted Neural Networks(CNN) to facilitate the process of identifying the analogous product. CNN techniques have been proven
to generate high accuracies in image matching problems
- Leverage Recurrent Neural Networks (RNN) to better replicate product lifecycle stages. Since RNN memory layers are better predictors of next
likely event, it is an apt tool to evaluate upcoming time-based performances
- Since the objective was to devise a scalable method, a cloud-ready easy to use UI was proposed, where user can upload the image of an upcom
ing style and the demand forecasts would be generated instantly
Overall Approach
The entire framework was developed in Python using Deep Learning platforms like Tensor Flow with an interactive user interface powered by
Django. The Deep Learning systems were supported through NVIDIA GPUs hosted on Google Cloud.
The demand prediction framework consists of following components to ensure an end to end analytical implementation and consumption.
In practice, CNN and RNN are two distinct methodologies and this article highlights a case where various Deep Learning models were combined
to develop a self-learning demand forecasting framework.
Affine www.affinenalytics.com
Affine Blog
New Product Forecasting using Deep Learning
- Input Image: holds raw pixel values of the image with features being width, height & RGB values
- Convolution: Conv Net is to extract features from input data. Formation of matrix by sliding filters over an image and computing dot product
is called“Feature Map”
- Non-Linearity – RELU: This layer applies element-wise activation filter leveraged to stimulate non-linearity relationships in a standard ANN
- Pooling: Reduces the dimensionality of each feature map and retains important information. Helps in arriving at a scale invariant
representation of an image
- Dropouts: To prevent overfitting random connections are severed
- SoftMax Layer: Output layer that classifies the image to appropriate category/subcategory/heel height classes
An image classification algorithm was developed by leveraging Deep Learning techniques like Convolution Neural Networks.
The process included
- Data collation
• Developed an Image bank consisting of multi-style shoes across all categories/sub-categories e.g. sports, fashion, formals etc.
Included multiple alignments of the shoe images
- Data cleaning and standardization
• Removed duplicate images
• Standardized the image to a desired format and size
- Define high-level features
• Few key features were defined like brands, sub-category, shoe design – color, heel etc.
- Image matching outcomes
• Implemented a CNN model with 5+ hidden layers
The following image is an illustrative representation of the CNN architecture implemented
1. Product Similarity Engine
Affine www.affinenalytics.com
Affine Blog
New Product Forecasting using Deep Learning
1. Forecasting Engine
A demand forecasting engine was developed on the available data by evaluating various factors like
• Promotions – Discounts, Markdown
• Pricing changes
• Seasonality – Holiday sales
• Average customer rating
• Product Attributes – This was sourced from the CNN exercise highlighted in the previous step
• Product Lifecycle – High sales in initial weeks followed by declining trend
Analogous Product: Attribute Similarity Snapshot (Sample Attributes Highlighted)
dentified Top N matching shoes and calculated their probability scores. Classified image orientation as top, side (right/left) alignment of the same
image:
Similarity Index- Calculated based on the normalized overall probability scores
The following image is an illustrative representation of the demand forecasting model based on RNN architecture
The RNN implementation was done using Keras Sequential model and the loss function was estimated using“mean squared error”method
Affine www.affinenalytics.com
Affine Blog
New Product Forecasting using Deep Learning
An illustrative snapshot is highlighted below:
The accuracy from the proposed Deep Learning framework was in the range of 85-90% which was an improvement on the existing methodology
of 60-65%.
Demand forecast outcome
Web UI for Analytical Consumption
Affine www.affinenalytics.com
Affine Blog
New Product Forecasting using Deep Learning
• Higher accuracy through better learning of the product lifecycle
• The overall process is self-learning and hence can be scaled quickly
• Automation of decision intensive processes like analogous product selection led to reduction in execution time
• Long-term cost benefits are higher
Benefits and Impact
Author
• The image matching process requires huge data to train
• The feature selection method can be an automated through unsupervised techniques like Deep Auto Encoders which will further improve
scalability
• Managing image data is a cost intensive process but it can be rationalized over time
• The process accuracies can be improved by creating a deeper architecture of the network and an additional one-time investment of GPU
configurations
Sourav Mazumdar - Senior Manager, Affine
Kuleesha Yadav – Data Scientist, Affine
Key Challenges and Opportunities
Affine www.affinenalytics.com
Affine Blog
New Product Forecasting using Deep Learning
For more information
Telephone: +91-8088811781
Email: info@affineanalytics.com

More Related Content

What's hot

Edu4Sure - Google Ads Fundamentals
Edu4Sure - Google Ads FundamentalsEdu4Sure - Google Ads Fundamentals
Edu4Sure - Google Ads Fundamentals
Edu4Sure
 
Digital branding
Digital brandingDigital branding
Digital branding
Saurabh Pandey
 
Search Engine Optimization - What's it about?
Search Engine Optimization -  What's it about?Search Engine Optimization -  What's it about?
Search Engine Optimization - What's it about?
Vũ Lê
 
Data warehousing
Data warehousingData warehousing
Data warehousing
Shruti Dalela
 
Twitter marketing basics ppt
Twitter marketing basics pptTwitter marketing basics ppt
Twitter marketing basics ppt
Abdulla Shareef Sheikh
 
Google adwords ppt by sushen jamwal
Google adwords ppt by sushen jamwalGoogle adwords ppt by sushen jamwal
Google adwords ppt by sushen jamwal
Sushen Jamwal
 
Michael porter 5 force model
Michael porter 5 force modelMichael porter 5 force model
Michael porter 5 force model
Narsee Monjee Institute of Management Studies
 
Latent Semantic Indexing and Analysis
Latent Semantic Indexing and AnalysisLatent Semantic Indexing and Analysis
Latent Semantic Indexing and Analysis
Mercy Livingstone
 
Facebook ads ppt
Facebook ads pptFacebook ads ppt
Facebook ads ppt
Sushen Jamwal
 
Image SEO
Image SEOImage SEO
Image SEO
KizieCooper
 
Market entry strategies
Market entry strategiesMarket entry strategies
Market entry strategies
Vineet Sansare
 
Prediction of Car Price using Linear Regression
Prediction of Car Price using Linear RegressionPrediction of Car Price using Linear Regression
Prediction of Car Price using Linear Regression
ijtsrd
 
Seo presentation
Seo presentationSeo presentation
Seo presentation
travel_affair
 
Text analytics in social media
Text analytics in social mediaText analytics in social media
Text analytics in social media
Jeremiah Fadugba
 
Competitive Analysis Powerpoint Presentation Slides
Competitive Analysis Powerpoint Presentation SlidesCompetitive Analysis Powerpoint Presentation Slides
Competitive Analysis Powerpoint Presentation Slides
SlideTeam
 
Marketo - The definitive guide to digital advertising
Marketo - The definitive guide to digital advertisingMarketo - The definitive guide to digital advertising
Marketo - The definitive guide to digital advertising
Duy, Vo Hoang
 
1.4 data warehouse
1.4 data warehouse1.4 data warehouse
1.4 data warehouse
Krish_ver2
 
Web analytics
Web analyticsWeb analytics
Web analytics
NVISH Solutions
 
LinkedIn Marketing PPT
LinkedIn Marketing PPTLinkedIn Marketing PPT
LinkedIn Marketing PPT
SoftProdigy - We know software!
 
Pay per click
Pay per clickPay per click
Pay per click
Projects Kart
 

What's hot (20)

Edu4Sure - Google Ads Fundamentals
Edu4Sure - Google Ads FundamentalsEdu4Sure - Google Ads Fundamentals
Edu4Sure - Google Ads Fundamentals
 
Digital branding
Digital brandingDigital branding
Digital branding
 
Search Engine Optimization - What's it about?
Search Engine Optimization -  What's it about?Search Engine Optimization -  What's it about?
Search Engine Optimization - What's it about?
 
Data warehousing
Data warehousingData warehousing
Data warehousing
 
Twitter marketing basics ppt
Twitter marketing basics pptTwitter marketing basics ppt
Twitter marketing basics ppt
 
Google adwords ppt by sushen jamwal
Google adwords ppt by sushen jamwalGoogle adwords ppt by sushen jamwal
Google adwords ppt by sushen jamwal
 
Michael porter 5 force model
Michael porter 5 force modelMichael porter 5 force model
Michael porter 5 force model
 
Latent Semantic Indexing and Analysis
Latent Semantic Indexing and AnalysisLatent Semantic Indexing and Analysis
Latent Semantic Indexing and Analysis
 
Facebook ads ppt
Facebook ads pptFacebook ads ppt
Facebook ads ppt
 
Image SEO
Image SEOImage SEO
Image SEO
 
Market entry strategies
Market entry strategiesMarket entry strategies
Market entry strategies
 
Prediction of Car Price using Linear Regression
Prediction of Car Price using Linear RegressionPrediction of Car Price using Linear Regression
Prediction of Car Price using Linear Regression
 
Seo presentation
Seo presentationSeo presentation
Seo presentation
 
Text analytics in social media
Text analytics in social mediaText analytics in social media
Text analytics in social media
 
Competitive Analysis Powerpoint Presentation Slides
Competitive Analysis Powerpoint Presentation SlidesCompetitive Analysis Powerpoint Presentation Slides
Competitive Analysis Powerpoint Presentation Slides
 
Marketo - The definitive guide to digital advertising
Marketo - The definitive guide to digital advertisingMarketo - The definitive guide to digital advertising
Marketo - The definitive guide to digital advertising
 
1.4 data warehouse
1.4 data warehouse1.4 data warehouse
1.4 data warehouse
 
Web analytics
Web analyticsWeb analytics
Web analytics
 
LinkedIn Marketing PPT
LinkedIn Marketing PPTLinkedIn Marketing PPT
LinkedIn Marketing PPT
 
Pay per click
Pay per clickPay per click
Pay per click
 

Similar to New Product Forecasting Using Deep Learning

82_PHOTOLAB-----Project PPT.pdfhejeenejsn
82_PHOTOLAB-----Project PPT.pdfhejeenejsn82_PHOTOLAB-----Project PPT.pdfhejeenejsn
82_PHOTOLAB-----Project PPT.pdfhejeenejsn
shivam003d
 
major ppt.pptx
major ppt.pptxmajor ppt.pptx
major ppt.pptx
AnushaG52
 
Building a guided analytics forecasting platform with Knime
Building a guided analytics forecasting platform with KnimeBuilding a guided analytics forecasting platform with Knime
Building a guided analytics forecasting platform with Knime
Knoldus Inc.
 
Sdpl1
Sdpl1Sdpl1
Advertiser Analytics
Advertiser AnalyticsAdvertiser Analytics
Advertiser Analytics
randeepbhatia
 
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
Value Amplify Consulting
 
Providing Highly Accurate Service Recommendation over Big Data using Adaptive...
Providing Highly Accurate Service Recommendation over Big Data using Adaptive...Providing Highly Accurate Service Recommendation over Big Data using Adaptive...
Providing Highly Accurate Service Recommendation over Big Data using Adaptive...
IRJET Journal
 
Mobile shopping
Mobile shoppingMobile shopping
Mobile shopping
TejveerSingh93
 
Assured quality at low cost through Instrument Cluster testing for a global a...
Assured quality at low cost through Instrument Cluster testing for a global a...Assured quality at low cost through Instrument Cluster testing for a global a...
Assured quality at low cost through Instrument Cluster testing for a global a...
Mindtree Ltd.
 
MMRSS Usability Engineering
MMRSS Usability EngineeringMMRSS Usability Engineering
MMRSS Usability Engineering
MajesticMRSS
 
IRJET-Smart Tourism Recommender System
IRJET-Smart Tourism Recommender SystemIRJET-Smart Tourism Recommender System
IRJET-Smart Tourism Recommender System
IRJET Journal
 
Majestic MRSS Usability Engineering
Majestic MRSS Usability EngineeringMajestic MRSS Usability Engineering
Majestic MRSS Usability Engineering
Majestic MRSS
 
2014 IEEE DOTNET DATA MINING PROJECT Product aspect-ranking-and--its-applicat...
2014 IEEE DOTNET DATA MINING PROJECT Product aspect-ranking-and--its-applicat...2014 IEEE DOTNET DATA MINING PROJECT Product aspect-ranking-and--its-applicat...
2014 IEEE DOTNET DATA MINING PROJECT Product aspect-ranking-and--its-applicat...
IEEEMEMTECHSTUDENTSPROJECTS
 
IEEE 2014 DOTNET DATA MINING PROJECTS Product aspect-ranking-and--its-applica...
IEEE 2014 DOTNET DATA MINING PROJECTS Product aspect-ranking-and--its-applica...IEEE 2014 DOTNET DATA MINING PROJECTS Product aspect-ranking-and--its-applica...
IEEE 2014 DOTNET DATA MINING PROJECTS Product aspect-ranking-and--its-applica...
IEEEMEMTECHSTUDENTPROJECTS
 
Software Operation Knowledge
Software Operation KnowledgeSoftware Operation Knowledge
Software Operation Knowledge
Devnology
 
Fundamentals of software development
Fundamentals of software developmentFundamentals of software development
Fundamentals of software development
Pratik Devmurari
 
software engineering
software engineering software engineering
software engineering
bharati vidhyapeeth uni.-pune
 
CS-422 THESIS (1).pptx
CS-422 THESIS (1).pptxCS-422 THESIS (1).pptx
CS-422 THESIS (1).pptx
poojagupta010
 
Synopsis on inventory_management_system
Synopsis on inventory_management_systemSynopsis on inventory_management_system
Synopsis on inventory_management_system
Divya Baghel
 
How to Build an AI/ML Product and Sell it by SalesChoice CPO
How to Build an AI/ML Product and Sell it by SalesChoice CPOHow to Build an AI/ML Product and Sell it by SalesChoice CPO
How to Build an AI/ML Product and Sell it by SalesChoice CPO
Product School
 

Similar to New Product Forecasting Using Deep Learning (20)

82_PHOTOLAB-----Project PPT.pdfhejeenejsn
82_PHOTOLAB-----Project PPT.pdfhejeenejsn82_PHOTOLAB-----Project PPT.pdfhejeenejsn
82_PHOTOLAB-----Project PPT.pdfhejeenejsn
 
major ppt.pptx
major ppt.pptxmajor ppt.pptx
major ppt.pptx
 
Building a guided analytics forecasting platform with Knime
Building a guided analytics forecasting platform with KnimeBuilding a guided analytics forecasting platform with Knime
Building a guided analytics forecasting platform with Knime
 
Sdpl1
Sdpl1Sdpl1
Sdpl1
 
Advertiser Analytics
Advertiser AnalyticsAdvertiser Analytics
Advertiser Analytics
 
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
AI Class Topic 3: Building Machine Learning Predictive Systems (Predictive Ma...
 
Providing Highly Accurate Service Recommendation over Big Data using Adaptive...
Providing Highly Accurate Service Recommendation over Big Data using Adaptive...Providing Highly Accurate Service Recommendation over Big Data using Adaptive...
Providing Highly Accurate Service Recommendation over Big Data using Adaptive...
 
Mobile shopping
Mobile shoppingMobile shopping
Mobile shopping
 
Assured quality at low cost through Instrument Cluster testing for a global a...
Assured quality at low cost through Instrument Cluster testing for a global a...Assured quality at low cost through Instrument Cluster testing for a global a...
Assured quality at low cost through Instrument Cluster testing for a global a...
 
MMRSS Usability Engineering
MMRSS Usability EngineeringMMRSS Usability Engineering
MMRSS Usability Engineering
 
IRJET-Smart Tourism Recommender System
IRJET-Smart Tourism Recommender SystemIRJET-Smart Tourism Recommender System
IRJET-Smart Tourism Recommender System
 
Majestic MRSS Usability Engineering
Majestic MRSS Usability EngineeringMajestic MRSS Usability Engineering
Majestic MRSS Usability Engineering
 
2014 IEEE DOTNET DATA MINING PROJECT Product aspect-ranking-and--its-applicat...
2014 IEEE DOTNET DATA MINING PROJECT Product aspect-ranking-and--its-applicat...2014 IEEE DOTNET DATA MINING PROJECT Product aspect-ranking-and--its-applicat...
2014 IEEE DOTNET DATA MINING PROJECT Product aspect-ranking-and--its-applicat...
 
IEEE 2014 DOTNET DATA MINING PROJECTS Product aspect-ranking-and--its-applica...
IEEE 2014 DOTNET DATA MINING PROJECTS Product aspect-ranking-and--its-applica...IEEE 2014 DOTNET DATA MINING PROJECTS Product aspect-ranking-and--its-applica...
IEEE 2014 DOTNET DATA MINING PROJECTS Product aspect-ranking-and--its-applica...
 
Software Operation Knowledge
Software Operation KnowledgeSoftware Operation Knowledge
Software Operation Knowledge
 
Fundamentals of software development
Fundamentals of software developmentFundamentals of software development
Fundamentals of software development
 
software engineering
software engineering software engineering
software engineering
 
CS-422 THESIS (1).pptx
CS-422 THESIS (1).pptxCS-422 THESIS (1).pptx
CS-422 THESIS (1).pptx
 
Synopsis on inventory_management_system
Synopsis on inventory_management_systemSynopsis on inventory_management_system
Synopsis on inventory_management_system
 
How to Build an AI/ML Product and Sell it by SalesChoice CPO
How to Build an AI/ML Product and Sell it by SalesChoice CPOHow to Build an AI/ML Product and Sell it by SalesChoice CPO
How to Build an AI/ML Product and Sell it by SalesChoice CPO
 

Recently uploaded

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
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
Social Samosa
 
The Ipsos - AI - Monitor 2024 Report.pdf
The  Ipsos - AI - Monitor 2024 Report.pdfThe  Ipsos - AI - Monitor 2024 Report.pdf
The Ipsos - AI - Monitor 2024 Report.pdf
Social Samosa
 
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
 
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
 
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
 
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdfUdemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Fernanda Palhano
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
Bill641377
 
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
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
roli9797
 
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
 
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(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
74nqk8xf
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
g4dpvqap0
 
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
 
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Aggregage
 
The Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series DatabaseThe Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series Database
javier ramirez
 
Influence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business PlanInfluence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business Plan
jerlynmaetalle
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
rwarrenll
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Kiwi Creative
 

Recently uploaded (20)

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
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
 
The Ipsos - AI - Monitor 2024 Report.pdf
The  Ipsos - AI - Monitor 2024 Report.pdfThe  Ipsos - AI - Monitor 2024 Report.pdf
The Ipsos - AI - Monitor 2024 Report.pdf
 
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
 
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
 
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
 
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdfUdemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
 
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...
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
 
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
 
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(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
一比一原版(Chester毕业证书)切斯特大学毕业证如何办理
 
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理一比一原版(爱大毕业证书)爱丁堡大学毕业证如何办理
一比一原版(爱大毕业证书)爱丁堡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...
 
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
Beyond the Basics of A/B Tests: Highly Innovative Experimentation Tactics You...
 
The Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series DatabaseThe Building Blocks of QuestDB, a Time Series Database
The Building Blocks of QuestDB, a Time Series Database
 
Influence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business PlanInfluence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business Plan
 
My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.My burning issue is homelessness K.C.M.O.
My burning issue is homelessness K.C.M.O.
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
 

New Product Forecasting Using Deep Learning

  • 2. Affine www.affinenalytics.com Affine Blog New Product Forecasting using Deep Learning Background Forecasting demand for new product launches has been a major challenge for industries and cost of error has been high. Under predict demand and you lose on potential sales, overpredict them and there is excess inventory to take care of. Multiple research suggests that new product contributes to one-third of the organization sales across the various industry. Industries like Apparel Retailer or Gaming thrive on new launches and innovation, and this number can easily inflate to as high as 70%. Hence accuracy of demand forecasts has been a top priority for marketers and inventory planning teams. There are a whole lot of analytics techniques adopted by analysts and decision scientists to better forecast potential demand, the popular ones being: - Market Test Methods – Delphi/Survey based exercise - Diffusion modeling - Conjoint & Regression based look alike models While Market Test Methods are still popular but they need a lot of domain expertise and cost intensive processes to drive desired results. In recent times, techniques like Conjoint and Regression based methods are more frequently leveraged by marketers and data scientists. A typical demand forecasting process for the same is highlighted below: Though the process implements an analytical temper of quantifying cross synergies between business drivers and is scalable enough to generate dynamic business scenarios on the go, it falls short of expectations on following two aspects It includes heuristics exercise of identifying analogous products by manually defining product similarity. Besides, the robustness of this exercise is influenced by domain expertise. The manual process coupled with subjectivity of the process might lead to questionable accuracy standards It is still a supervised model and the key demand drivers need manual tuning to generate better forecasting accuracy For retailers and manufacturers esp. apparel, food, etc. where the rate of innovation is high and assortments keep refreshing from season to season, a heuristic method would lead to high cost and error for any demand forecasting exercise.` Since the primary reason of including product features in demand forecasting model is to under- stand cognitive influence on customer purchase behavior, a deep learning framework is a better and accurate approach to capture the same
  • 3. Case Background An apparel retailer wanted to forecast demand for its newly launched “Footwear” styles across various lifecycle stages. The current forecasting engine implemented various supervised techniques which were ensemble to generate desired demand forecasting. It had 2 major shortcomings: - The analogous product selection mechanism was heuristic and lead to low accuracy level in downstream processes - The heuristic exercise was a significant road block in evolving the current process to a scalable architecture, making the overall experience a cost intensive one - The engine was not able to replicate the product life cycle accurately Proposed Solution We proposed to tackle the problem through an intelligent, automated and scalable framework - Leverage Convoluted Neural Networks(CNN) to facilitate the process of identifying the analogous product. CNN techniques have been proven to generate high accuracies in image matching problems - Leverage Recurrent Neural Networks (RNN) to better replicate product lifecycle stages. Since RNN memory layers are better predictors of next likely event, it is an apt tool to evaluate upcoming time-based performances - Since the objective was to devise a scalable method, a cloud-ready easy to use UI was proposed, where user can upload the image of an upcom ing style and the demand forecasts would be generated instantly Overall Approach The entire framework was developed in Python using Deep Learning platforms like Tensor Flow with an interactive user interface powered by Django. The Deep Learning systems were supported through NVIDIA GPUs hosted on Google Cloud. The demand prediction framework consists of following components to ensure an end to end analytical implementation and consumption. In practice, CNN and RNN are two distinct methodologies and this article highlights a case where various Deep Learning models were combined to develop a self-learning demand forecasting framework. Affine www.affinenalytics.com Affine Blog New Product Forecasting using Deep Learning
  • 4. - Input Image: holds raw pixel values of the image with features being width, height & RGB values - Convolution: Conv Net is to extract features from input data. Formation of matrix by sliding filters over an image and computing dot product is called“Feature Map” - Non-Linearity – RELU: This layer applies element-wise activation filter leveraged to stimulate non-linearity relationships in a standard ANN - Pooling: Reduces the dimensionality of each feature map and retains important information. Helps in arriving at a scale invariant representation of an image - Dropouts: To prevent overfitting random connections are severed - SoftMax Layer: Output layer that classifies the image to appropriate category/subcategory/heel height classes An image classification algorithm was developed by leveraging Deep Learning techniques like Convolution Neural Networks. The process included - Data collation • Developed an Image bank consisting of multi-style shoes across all categories/sub-categories e.g. sports, fashion, formals etc. Included multiple alignments of the shoe images - Data cleaning and standardization • Removed duplicate images • Standardized the image to a desired format and size - Define high-level features • Few key features were defined like brands, sub-category, shoe design – color, heel etc. - Image matching outcomes • Implemented a CNN model with 5+ hidden layers The following image is an illustrative representation of the CNN architecture implemented 1. Product Similarity Engine Affine www.affinenalytics.com Affine Blog New Product Forecasting using Deep Learning
  • 5. 1. Forecasting Engine A demand forecasting engine was developed on the available data by evaluating various factors like • Promotions – Discounts, Markdown • Pricing changes • Seasonality – Holiday sales • Average customer rating • Product Attributes – This was sourced from the CNN exercise highlighted in the previous step • Product Lifecycle – High sales in initial weeks followed by declining trend Analogous Product: Attribute Similarity Snapshot (Sample Attributes Highlighted) dentified Top N matching shoes and calculated their probability scores. Classified image orientation as top, side (right/left) alignment of the same image: Similarity Index- Calculated based on the normalized overall probability scores The following image is an illustrative representation of the demand forecasting model based on RNN architecture The RNN implementation was done using Keras Sequential model and the loss function was estimated using“mean squared error”method Affine www.affinenalytics.com Affine Blog New Product Forecasting using Deep Learning
  • 6. An illustrative snapshot is highlighted below: The accuracy from the proposed Deep Learning framework was in the range of 85-90% which was an improvement on the existing methodology of 60-65%. Demand forecast outcome Web UI for Analytical Consumption Affine www.affinenalytics.com Affine Blog New Product Forecasting using Deep Learning
  • 7. • Higher accuracy through better learning of the product lifecycle • The overall process is self-learning and hence can be scaled quickly • Automation of decision intensive processes like analogous product selection led to reduction in execution time • Long-term cost benefits are higher Benefits and Impact Author • The image matching process requires huge data to train • The feature selection method can be an automated through unsupervised techniques like Deep Auto Encoders which will further improve scalability • Managing image data is a cost intensive process but it can be rationalized over time • The process accuracies can be improved by creating a deeper architecture of the network and an additional one-time investment of GPU configurations Sourav Mazumdar - Senior Manager, Affine Kuleesha Yadav – Data Scientist, Affine Key Challenges and Opportunities Affine www.affinenalytics.com Affine Blog New Product Forecasting using Deep Learning For more information Telephone: +91-8088811781 Email: info@affineanalytics.com