O slideshow foi denunciado.
Utilizamos seu perfil e dados de atividades no LinkedIn para personalizar e exibir anúncios mais relevantes. Altere suas preferências de anúncios quando desejar.

Data Science for Marketing

This presentation slide introduces Data Science to Maketing Professionals. This intent to explain how to think like a data scientist in term of marketing concept which focus on consumer behaviors and new set of big data (web, social, location.. etc). The reference books are at the end of the slides.

Data Science for Marketing

  1. 1. Data Science for Marketing Dr. Komes Chandavimol December 27, 2020
  2. 2. My DBA Journey
  3. 3. Data Science for Business The overview
  4. 4. Today Data
  5. 5. Today Data
  6. 6. 2020 Today Data (Machine + Human)
  7. 7. Advance of Technology
  8. 8. Advance of Technology
  9. 9. How to combine (Big) Data, Advance of Technology to bring value?
  10. 10. http://dataofthings.blogspot.com/2014/04/the-bbbt-sessions-hortonworks-big-data.html Copyright 2019 Komes Chandavimol. All Rights Reserved More Data, More Value, become Intelligence
  11. 11. Copyright 2020 Komes Chandavimol. All Rights Reserved Data Intelligence by business value 4 Levels of Analytics
  12. 12. Data Intelligence to Data Science
  13. 13. Data New Analytic Insights (Information, knowledge, data story) Data Product + VisualizationMass Analytic Tools Data Mining/Machine Learning Recommender systems Complex Event Processing Data Science Team Data Scientist Datafication Copyright 2020 Komes Chandavimol. All Rights Reserved 13 “The ability to take data — to be able to understand it, to process it, to extract VALUE from it, to visualize it, to communicate it — that’s going to be a hugely important skill in the next decades.” Data Science
  14. 14. People Analytics: Hiring, Reskills, Churn Data sources: Historical hiring attributes Data products: Predictive model – recruiting, Personalized Development, Churn Prediction, Talent Identification Behavioral Test Situational Test GPA Brain Teaser Good School http://www.kornferryinstitute.com/briefings-magazine/summer-2014/big-data-predictive-analytics-and-hiring
  15. 15. Fraud Detection Data sources: historical pattern of transaction data Data products: predictive models – fraud/non-fraud, Anomaly Detection https://bluefishway.com/2013/09/13/panic-oh-no-not-again/ http://blogs.wsj.com/cio/2015/08/25/paypal-fights-fraud-with-machine-learning-and-human-detectives/
  16. 16. Predictive Maintenance Data sources: IoT Sensors in factory Data products: predictive maintenance models http://www.electrex.it/en/news/600-automated-energy-management-system-a-enms-for-cement-production-plants.ht http://www.digitalistmag.com/digital-economy/2015/12/01/iot-digitization-reinforce-cement-industry-03814141
  17. 17. Fuel Saving Data sources: Telematics (sensor), GPS Data products: Prescriptive analytics – route optimization, predictive maintenance (parts/malfunction) http://www.cnet.com/news/ups-turns-data-analysis-into-big-savings/ http://www.cnet.com/news/ups-turns-data-analysis-into-big-savings/ Credit: Jarun Ngamvirojcharoen
  18. 18. Recommendation System Data sources: Click Streams, Customer Behaviors Data products: Prescriptive analytics – Personalized Marketing, Recommended Pages Personalized Shopping Experience Data sources: Click Steam, Customer History, Call Center ID Data products: Omni- Channel Prediction, Customer Journey
  19. 19. Rolls-Royce Data Labs Data Scientist, Visualization Specialist, Data Engineer, Business Analytics https://www.youtube.com/watch?v=AOdH9aZVdaE
  20. 20. Data Science Tools: Machine Learning
  21. 21. Data Science Tools & Platforms 2000 2019 https://twitter.com/Chuck_Moeller/status/1341060434800107527?s=20
  22. 22. Data Science Tools & Platforms
  23. 23. Data Science Tools & Platforms
  24. 24. Data Science for Marketing
  25. 25. Joseph Rivera (2019)
  26. 26. Insights An insight has to contain new information An insight has to quantify causality An insight must focus on understanding consumer behaviors An insight has to provide a competitive advantage An insight must generate financial implications
  27. 27. • What Drive Demand? • Who is most likely to buy and how do I target them? • When are my customers most likely to buy? https://tambbideas.web.app/w-vs-v-recovery.html
  28. 28. What Drive Demand? Marketing problems: determining and quantifying those things that drive demand. https://tambbideas.web.app/w-vs-v-recovery.html
  29. 29. Technical discussion
  30. 30. Data Science Life Cycles Data Sources Data Preparation & Engineering Modeling
  31. 31. Reference Papers (Advance Topics)
  32. 32. Who is most likely to buy and how do I target them? The next marketing question is around targeting, particularly who is likely to buy. http://www.experian.com/blogs/marketing-forward/2014/06/24/high-definition-customer-profiles-a- clapperboard-for-marketers/
  33. 33. Technical discussion
  34. 34. Data Science Workflow Data Sources Data Preparation & Engineering Modeling
  35. 35. Reference Papers (Advance Topics)
  36. 36. When are my customers most likely to buy? • The next marketing question is ‘WHEN’ is an event (purchase, response, churn, etc) zzz
  37. 37. Technical discussion
  38. 38. Technical discussion
  39. 39. Data Science Life Cycles Data Sources Data Preparation & Engineering Modeling
  40. 40. Reference Papers (Advance Topics)
  41. 41. MARKETING + DATA + SCIENCE Future Topics for Research
  42. 42. Cioffi, R., 2019. DATA-DRIVEN MARKETING: Strategies, metrics and infrastructures to optimize the marketing performances (Doctoral dissertation, Politecnico di Torino).
  43. 43. Visualization Foundation Methods 1. Perception Mapping – Multidimension scaling (MDS) – Join Space Mapping 2. Feature Grouping – Factor Analysis
  44. 44. Visualization: Perception Mapping . Multidimension scaling (MDS) vs Join Space Mapping https://feedbackjuice.com/marketing-research-analysis/multidimmensional-scaling/ https://www.perceptualmaps.com/map-format/
  45. 45. Visualization: Feature Mapping Factor Analytics
  46. 46. Visualization: Feature Mapping https://www.datacamp.com/community/tutorials/introduction-factor-analysis
  47. 47. Visualization Advanced Methods 1. Frequency based perceptual mapping – Correspondence analysis 2. Feature importance in marketing – Conjoint analysis 3. Feature importance (text ) – LDA: Latent Dirichlet allocation 4. Temporal weighting scheme
  48. 48. Visualization: Correspondence Analysis http://www.sthda.com/english/articles/31-principal-component-methods-in-r- practical-guide/113-ca-correspondence-analysis-in-r-essentials/
  49. 49. Visualization: Correspondence Analysis http://www.sthda.com/english/articles/31-principal-component-methods-in-r- practical-guide/113-ca-correspondence-analysis-in-r-essentials/
  50. 50. Visualization: Conjoint Analysis https://www.questionpro.com/blog/what-is-conjoint-analysis/
  51. 51. Visualization Big Data and Analytics 1. Perception Mapping in Big Data 2. Customer Relationship Management 3. Parallel coordinates approach 4. OpinionSeer
  52. 52. Parallel coordinates approach https://www.serendipidata.com/posts/visualizing-high-dimensional-data
  53. 53. Perception Mapping in Big Data https://link.springer.com/article/10.1007/s40558-015-0033-
  54. 54. CRM in Big Data
  55. 55. Parallel coordinates approach
  56. 56. OpinionSeer
  57. 57. Segmentation
  58. 58. Segmentation RFM (Recency, Frequency, Monetary) https://clevertap.com/blog/rfm-analysis/
  59. 59. Segmentation K-Mean Reference: https://www.softnix.co.th/
  60. 60. Segmentation Latent Class Analysis
  61. 61. Reference

×