Big Data Analytics
Propensity to buy online - offline
This analytics algorithm predict the probability of a customer to buy a given item. Analyzing the characteristics of previous customer whom bought the item
If could be used cross-selling, for example, customers how bought a Home insurance with higher probability to buy a Car Insurance or add additional features to their existing policies
It could analyze demographics data, from USA Census, and determine the areas with higher conversion rates or with higher deal revenue. This way is can be used to optimize online marketing campaigns
Different users have different tastes and likes. A one size fit all marketing strategy will underperform and deliver a poor ROI
This kind of analytic algorithms has the ability to segment your customers in different groups that shares the same demographics characteristics or buying behaviour. In order to create a personalized marketing campaign that will deliver the right message to the right user at the right time via the right channel.
These groups could be used to create new offers or promotions
This kind of analytics algorithm compare the past searches and purchases of the user with other customers with the same likes. Then it can suggest new policies based on the previous behaviour
It can be applied even when we don't have futher information about user previous behaviour, the so called "non personalized recommendation".
The typical approach suggest new policies to our users, but we can look at the reverse path. For example, we want fo promote a policy, the algorithm can select the users with the higher conversion rates for a personalized marketing campaign