Life insurance is a competitive business. Due to uncertainty and rising costs, insurance companies want to increase growth by acquiring and retaining the most profitable customers.
This is a marketing project from a life insurance firm headquartered in Singapore. The firm is helping their branch in Philippines to make a data-driven strategic planning on their products. Obviously, from a marketing perspective, the firm needs to predict and try to identify people who will buy insurance, so that they can save time and money for the most profitable customers. Other objectives include getting a better understanding of the products or cover types to recommend or promote to potential customers.
Data collected is about everyone they have contacted to promote their insurance services. It consists of 33 attributes of each policy purchased by customers for themselves and their loved ones.
-
Are there seasonal purchase behaviours in the products or cover types? There could be seasons/time that will alter a person's willingness to buy. Seasonal influences need to be identified so that the marketing team can identify the best time to market certain insurance policies to potential customers. In so doing, the team can often influence/dictate, how, and when potential customers will spend their money.
-
Suggests a number of optimal customer segments and their key personas.
The goal here is to group the customer data to different clusters, using unsupervised learning technique (KMeans clustering). In such a way, each cluster will consist of features that will distinguish one from the other. And this will guide the marketing team to estimate how much the monthly/annual premiums potential customers are willing to pay and/or what policy the customer will most likely to purchase.