Company websites, Social Media, News Media, Government Datasets, Weather Datasets, Open Source Intelligence.
Tuned against internal data to deliver customer insights and behavioral predictions.
Data is continuously ingested, cleaned, structured, normalized and streamed through Relativity6 proprietary machine learning APIs.
Identify customers' propensity to purchase.
Recognize accurate cross-sell and upsell opportunities.
Know when each customer is most likely to purchase.
Recommend most efficient sales channel per customer.
Through research at MIT, Relativity6 concluded that in order to generate the most accurate predictions possible, we needed to tune our algorithms strictly into objective, unbiased data.
This is why we focus our data inputs on internal customer data, specifically the actions and behaviors taken by your customers in the past. Our technology is able to seamlessly ingest both structured and unstructured data sources and filter out only the features that are directly related to purchasing activity.
We call our proprietary system of algorithms 'behavioral listening algorithms' because we've trained our models to tune into strictly action based variables, leaving subjectivity to the side.
A Latin American insurer with over $1B in Direct Written Premiums, was experiencing a steady increase in policy churn rates over time, as well as an increasing trend of lapsed policies.
Despite churn models created by their internal data science team, the insurer began looking for external solutions to improve customer retention.
Relativity6 set out to improve the insurer’s retention rates by using proprietary algorithms and an insurance product recommendation engine.
Relativity6 worked with a Global banking partner to segment customer behaviors by engagement propensity and activity.
Relativity6 worked with a Latin American retailer to segment customers by propensity to purchase.
Using the retailers internal data, Relativity6 ran machine learning algorithms to segment customers and recommend products based off transactions.
Relativity6 worked with the branded home décor line to identify inactive customers with a high propensity to repurchase.
Our win-back and cross sell predictions delivered 250% return on revenue for the client.
Relativity6 worked with Zipcar to identify which inactive members had the highest probability of making a booking and analyzed the type of vehicle these customers were most likely to request.
Using Relativity6's proprietary machine learning algorithms, we launched a targeted campaign to these members to increase their incentive to make an immediate purchase.