Share in our experience of customer insight and data management

Back

Made for each other: Celebrus and Data Science

Published: Thursday, 9th August 2018 by Pragati Jain, Data Analytics

The rich breadth of data that Celebrus captures makes it one of the best sources for use in more advanced analytics and data science initiatives such as real-time propensity scoring, predicting purchase behaviour or serving personalised offers to customers. Capturing data in real time and using Machine Learning models - along with the ability to execute without involving too many additional systems - means that while other data science initiatives are still on the drawing board, our clients can test and implement real world projects such as:

  • Real-Time Scoring: Already used in multiple areas such as detecting fraudulent credit-card transactions and product recommendations to customers while browsing products online. These use machine learning algorithms like Random Forests, Support Vector Machines, Naive Bayes among others.
  • Predicting Customer's Purchase Behaviour: Celebrus captures a lot of relevant information from retail websites like pages visited, products browsed by customers online and products added to baskets. Considering customer's historical data related to product purchase, we can predict whether the customer will make a purchase in the future or not, or what kind of sales will happen at a later date, and whether sales will increase or not. Learning algorithms like Logistic Regression, Decision Trees, Neural Networks, etc. are typically used to predict purchase behaviour.
  • Product Recommendation to Customers: offers related to products already purchased or browsed by customers are typically provided by using clustering algorithms like K-Means. Implementation of this can be seen in areas like telecommunication, where companies try to target customers with similar monthly usage of data plans, for sending out targeted offers based on their monthly usage.

A typical process looks like -

Diagram showing a typical process

A suggested approach would be to start simply and iterate towards a more complex model to improve accuracy and confidence while at the same time proving its business value. Once you have done this, you can calculate the return-on-investment and if appropriate migrate it to a production ready environment.

To find out more about how Celebrus data can be used to underpin data science initiatives, why not speak to our Celebrus Customer Success team – contact us now.

×

Privacy settings

At D4t4 we are all the about the data. We are serious about data protection and your privacy so we will only collect your personal data and use it with your permission. We use cookies to collect statistics to optimise website functionality and deliver content tailored to your interests.

Our three categories of collection are detailed below.

Essential browsing only We will only collect the essential data required to enable core site functionality. We will not collect any personally identifiable information or behavioural data.
Browse anonymously We will only collect your browsing behaviour on the website to help understand our customers' needs and improve the experience for everyone. We will not collect any personally identifiable information so we won't know who you are.
Personalised experience We will only collect information that allows us to identify you and make your browsing experience as smooth as possible by remembering your log in details and saved items. In the course of dealing with you, we may need to pass your personal data on to third-party service providers contracted to D4t4 Solutions.

You will be able to change your options at any time by clicking the Privacy settings link and our full Privacy Statement can be viewed by clicking the relevant link.

v20180607