What should we do next?

Forming Analytical Questions

Konstantinos Kattidis

Data Analytics Lead

Understanding what should be done

Predictive analytics answers questions about the future

Prescriptive analytics goes a step further to prescribe the course of action.

Business question:

How can we recommend relevant products to our customers to increase sales?

Analytical question:

How can we develop an algorithm to recommend relevant products to customers, based on relevant variables?

Technique:

Workflow of the product recommendation algorithm

Business question:

How can we detect and prevent bank fraud in real-time to protect our customers and minimize financial losses?

Analytical question:

How can we identify fraudulent behavior in our data, and automatically prescribe the best course of action?

Technique:

Workflow of the bank fraud recommendation algorithm

Business question:

What marketing strategies should we use to reduce customer churn?

Analytical question:

How can we develop a model to identify customers who are at risk of churning and prescribe the most effective marketing strategies to retain them?

Technique:

Workflow of the marketing strategies recommendation algorithm

Business question:

How can we optimize airline ticket prices in real-time to maximize sales?

Analytics questions:

Descriptive analytics: What ticket prices in the past resulted in higher revenue?
Diagnostic analytics: Why have the ticket prices last week result in sub-optimal profits?
Predictive analytics: What is the expected customer demand in the coming weeks?

Prescriptive analytics: What is the optimal price for a specific flight at a specific time to maximize sales?

Technique:

Outcome:

Dynamic adjustment of prices considering the following variables:
- Customer demand
- Fuel prices
- Weather

Recommendation algorithm workflow

Forming Analytical Questions