Ce diaporama a bien été signalé.
Nous utilisons votre profil LinkedIn et vos données d’activité pour vous proposer des publicités personnalisées et pertinentes. Vous pouvez changer vos préférences de publicités à tout moment.

Measuring the benefit effect for customers with Bayesian predictive modeling

795 vues

Publié le

Strata 2015 London presentation

Publié dans : Données & analyses
  • Identifiez-vous pour voir les commentaires

Measuring the benefit effect for customers with Bayesian predictive modeling

  1. 1. Measuring benefit effect for customers with bayesian prediction modeling Kwon, JeongMin (cojette@gmail.com) Strata + Hadoop World 2015, London
  2. 2. Offering
  3. 3. Offering • Popular way to promote products
  4. 4. Offering Process
  5. 5. Step 1: Customer Data Management Monitor customers’ actions Keeping track of customer data and information Defining goals
  6. 6. Step 2: Targeting Customer segmentation and selection with goals at step 1 Based on demographic information and log collections Statistical methods and data mining algorithms
  7. 7. Step 3: Offering Benefit (Campaign) • Delivering proper benefits to targeted customer groups • Methods: Promotion, Event, Advertisement and others • Measurement and prediction of campaign effects
  8. 8. How to measure and predict
  9. 9. How to compare offering effects
  10. 10. Multivariate Testing • Technique for testing a hypothesis with multiple variables • Issues for offering • Lack of long-term prediction • data, benefit limitations (Image from https://www.ownedit.com/features)
  11. 11. Bayesian Interpretation • Diachronic Interpretation • Probability of the hypotheses changes over time • Prior and posterior based on background information • Good for simulation, decision and prediction (Image from http://en.wikipedia.org/wiki/Bayes%27_theorem)
  12. 12. CausalImpact • Based on the paper [Inferring causal impact using Bayesian structural time-series models], Google, 2014 • CausalImpact Package in R • https://github.com/google/CausalImpact (Image from the paper)
  13. 13. CompareImpacts • Integration of bayesian time series prediction model with multivariate tests • For simple comparison of causal effects
  14. 14. Use Cases • Same offerings in various groups
  15. 15. Use Cases • Various offerings in a group
  16. 16. Basic Model • CausalImpact results
  17. 17. • Same offerings in three groups Use Case Results
  18. 18. • Offerings in a group with time differences Use Case Results
  19. 19. Office Hour: 15:25~16:05, Table A E-mail : cojette@gmail.com New Tool for Offering Comparison: Multivariate Test + Bayesian Time-Series Analysis