SlideShare a Scribd company logo

Rahul Shetty - Corporate relocation prediction - Codemotion Amsterdam 2019

•
•
Codemotion
Codemotion

Whenever you do something that nobody has tried to do before, you often encounter difficulties, that well, nobody has found before! During this talk we will walk you through the data, the modelling, the problems that we encountered and solutions while working together with Graydon on predicting whether different kinds of companies will of relocate. For this use case, we analyzed 10 years of data for two million companies using around 100 descriptors / features, and produced a predictive model using decision trees and random forests on Google Cloud Platform.

Related slideshows

Analytics
AnalyticsAnalytics
Analytics
 
Risk dk
Risk dkRisk dk
Risk dk
 
Body Media Poster
Body Media PosterBody Media Poster
Body Media Poster
 
1 of 18
Download to read offline
Corporate Relocation Prediction A 10 Year, 2 million company use case Rahul Shetty, Ana Maldonado, Mauricio Rodriguez Lara
Who We Are
Who We Are
Relocation Prediction use case Problem: businesses, schools, hospitals, etc. move locations over time (growth, bankruptcy, new markets, etc) Can we predict if they will relocate? - To where? - When? - Why? => For now, we focus only on relocation probability
For businesses we have historical Corporate Data: - Company size, credit rating, relocation, etc... => Can company characteristics predict relocation? - Useful information for service providers, realtors, city councils, investors and developers => Investigatory POC: 6 week study - Limit the scope to determine if relocation can be predicted, and if so, which properties can be a signal Relocation Prediction use case
(Big) Data We encountered some challenges: - Monthly data from branches of 2 million companies, going back 10 years… ~ 300 million rows - Disperse Data: where/how should it be gathered? - Monthly data too granular: how to aggregate? - Client did not have a suitable platform for data handling and analysis...
Data & Modeling Considerations - High dimensional time series data - Preserve the temporal granularity to maximize information - Neural Networks? - LSTM or CNNs? - NN design/exploration time > available time - Simplify data and modeling due to time constraints
Preparing the Data - Step 1: Collect the data on an appropriate platform: - Set up Google Cloud platform in one week - Step 2: Aggregate the Data - From monthly to yearly: predicted relocation based on yearly data - Choose how to deal with categorical variables - Subsequent Steps : Spawn virtual machine(s) on GCP for modeling
Summary Statistics - Final dataset: 75 features from 1 year and ‘has_relocated’ target from following year - 2 million entries per year - ~5% relocation (imbalanced dataset) - Goal: Build a model that can predict ‘has_relocated’ better than randomly (better than 95% accurate)
Modeling step 1: Exploring Models - Apply binary classification algorithms: SVM, logistic regression, decision trees (DT), random forests (RF) - Choose models with best performance: AUC, kappa - DTs and RF did best - Apply Sampling Techniques to improve models - Tune model parameters - Validate
Modeling step 2: ResultsTPR FPR AUC: 0.66 Best DT model produced by undersampling data, 5-fold CV, and DT parameters explored via grid search
Modeling Results: Features The most important features having an influence on a ‘has_relocated’ index were related to: - Company financial assessments and health - Company age
Validation How well can yearly models predict the next year’s relocation? AUC
Validation How well can yearly models predict the next year’s relocation? … in general, rather well AUC
Validation How well can yearly models predict the next year’s relocation? … in general, rather well … except for 2016 (?) AUC
- Company properties can be indicative of whether they relocate - Yearly aggregated data is sufficient for high level indications of relocation. - More granular modeling (e.g. with NN) may provide additional information Take aways - Possible to perform successful POC on big data within 6 weeks on GCP
Having had more time we would have: - Full time series modeling - NN, hierarchical modeling, etc... - Automate prediction, given company characteristics - Investigate anomalous year - Make use of modeling results: Future work
Any questions? rshetty@qualogy.com Thank you!

More Related Content

Rahul Shetty - Corporate relocation prediction - Codemotion Amsterdam 2019

  • 1. Corporate Relocation Prediction A 10 Year, 2 million company use case Rahul Shetty, Ana Maldonado, Mauricio Rodriguez Lara
  • 4. Relocation Prediction use case Problem: businesses, schools, hospitals, etc. move locations over time (growth, bankruptcy, new markets, etc) Can we predict if they will relocate? - To where? - When? - Why? => For now, we focus only on relocation probability
  • 5. For businesses we have historical Corporate Data: - Company size, credit rating, relocation, etc... => Can company characteristics predict relocation? - Useful information for service providers, realtors, city councils, investors and developers => Investigatory POC: 6 week study - Limit the scope to determine if relocation can be predicted, and if so, which properties can be a signal Relocation Prediction use case
  • 6. (Big) Data We encountered some challenges: - Monthly data from branches of 2 million companies, going back 10 years… ~ 300 million rows - Disperse Data: where/how should it be gathered? - Monthly data too granular: how to aggregate? - Client did not have a suitable platform for data handling and analysis...
  • 7. Data & Modeling Considerations - High dimensional time series data - Preserve the temporal granularity to maximize information - Neural Networks? - LSTM or CNNs? - NN design/exploration time > available time - Simplify data and modeling due to time constraints
  • 8. Preparing the Data - Step 1: Collect the data on an appropriate platform: - Set up Google Cloud platform in one week - Step 2: Aggregate the Data - From monthly to yearly: predicted relocation based on yearly data - Choose how to deal with categorical variables - Subsequent Steps : Spawn virtual machine(s) on GCP for modeling
  • 9. Summary Statistics - Final dataset: 75 features from 1 year and ‘has_relocated’ target from following year - 2 million entries per year - ~5% relocation (imbalanced dataset) - Goal: Build a model that can predict ‘has_relocated’ better than randomly (better than 95% accurate)
  • 10. Modeling step 1: Exploring Models - Apply binary classification algorithms: SVM, logistic regression, decision trees (DT), random forests (RF) - Choose models with best performance: AUC, kappa - DTs and RF did best - Apply Sampling Techniques to improve models - Tune model parameters - Validate
  • 11. Modeling step 2: ResultsTPR FPR AUC: 0.66 Best DT model produced by undersampling data, 5-fold CV, and DT parameters explored via grid search
  • 12. Modeling Results: Features The most important features having an influence on a ‘has_relocated’ index were related to: - Company financial assessments and health - Company age
  • 13. Validation How well can yearly models predict the next year’s relocation? AUC
  • 14. Validation How well can yearly models predict the next year’s relocation? … in general, rather well AUC
  • 15. Validation How well can yearly models predict the next year’s relocation? … in general, rather well … except for 2016 (?) AUC
  • 16. - Company properties can be indicative of whether they relocate - Yearly aggregated data is sufficient for high level indications of relocation. - More granular modeling (e.g. with NN) may provide additional information Take aways - Possible to perform successful POC on big data within 6 weeks on GCP
  • 17. Having had more time we would have: - Full time series modeling - NN, hierarchical modeling, etc... - Automate prediction, given company characteristics - Investigate anomalous year - Make use of modeling results: Future work