Sales Predictive Analytics
Predicting CLV (Customer Lifetime Value)
CLV - or the value of a customer in terms of profit/revenue over the long-term is a key business intelligence metric. CLV can determine the right amount of incentives or discounts to provide an existing customer for customer retention or their initial acquisition. Machine learning can accurately predict this value based on demographic data and past purchase or engagement behavior
Customer churn prediction (customer retention)
Prediction of the probability a customer will unsubscribe or switch to a competitor in the next quarter or year. Based on available customer behavioral data including purchase history, site visits & activity details, and calls to customer service. CLV can be used to decide what incentives or measures should be offered to retain a given customer.
Probability to close or purchase
Machine learning can provide accurate predictions of the probability a sales lead or opportunity will convert, close, or complete a certain purchase within a given quarter based on the same behavioral activity and demographic data as above. This allows prioritizing sales activity to the most promising sales pipeline opportunities and deprioritizing others. This includes spending online ad impression budgets more heavily on likely buyers. It can also be used to filter sales leads that are purchased in various ways.
Pricing elasticity prediction
Machine learning can predict the price that would trigger a purchase from a specific buyer, using again all the historic behavioral data available, including past purchases data and recent activity browsing various items - which show general interest as well as interest in a given item.
This enables businesses to offer a specific discount percentage (or other incentives) knowing that it is likely the maximum a customer would spend. This knowledge allows for sophisticated price discrimination & elasticity management for retail businesses.
Market segmentation analysis
By analyzing historical data for product or service price & features, purchases can be clustered into groups that are most popular. Clusters usually represent segments or "micro-segments" of desired price/feature profiles. By understanding these profiles products can be better developed to appeal to the micro-segments. Also, customer profiles can be built for customer preferences of a certain segment, thus allowing targeting/matching customers to appropriate products. This is related to recommendation engine profiling.