A predictive analytics primer
Download as PPTX, PDF1 like71 views
This document provides an overview of predictive analytics. It explains that predictive analytics uses data from the past to predict the future. The quality and amount of data is important, as the predictive model relies on the data it is trained on. Additionally, the underlying assumptions of the model can impact its accuracy, so they must be monitored over time to ensure the model still accurately predicts behavior as variables change. Managers should understand the data sources, assumptions, and outlier treatments used in any predictive models to have meaningful discussions and make informed business decisions.
Related topics:1 of 15
Download to read offline
More Related Content
What's hot (20)
Ad
Similar to A predictive analytics primer (20)
Ad
More from Raminder Singh (15)
A predictive analytics primer
- 1. A Predictive Analytics Primer
- 2. Based on the HBR article ‘A Predictive Analytics Primer’ by Thomas H. Davenport
- 3. No one has the ability to capture and analyze data from the future. However, there is a way to predict the future using data from the past It’s called Predictive Analytics
- 4. 2 basic points for better understanding
- 5. 1. The predictive model is as good as the data used to train it
- 6. Lack of good data is the most common barrier to organizations seeking to employ predictive analytics
- 7. Quality data along with high number of attributes and big size leads to more accurate predictions. It gives more number of factors and touchpoints to base the predictions on
- 8. Diversity in data also allows for more number of statistical models to choose from
- 9. 2. The underlying assumptions can make or break a predictive model. Every model has them, and it’s important to constantly monitor their impact
- 10. The big assumption in predictive analytics is that the future will continue to be like the past
- 11. If the model was created several years ago, it may no longer accurately predict current behavior
- 12. Or if a key variable got left out of the model, and that variable changed substantially over time, the output might go faulty
- 13. Some fundamental questions for Managers to keep in mind • Data source? • Underlying assumptions? • Outlier treatment?
- 14. This way a Manager Analyst duo can have meaningful conversations and drive business decisions with ease
- 15. Disclaimer: This presentation was created by Raminder Singh, under an internship by Prof. Mathur, IIM Lucknow