If for a particular product customers are recommended each month based on his intent and features. The recommended base is available to us for every month.
Lets say a customer doesn't take the product i.e. no conversions. If this happens repeatedly for some months consecutively that customer should not be recommended for the next month automatically.
We don't have to make recommendations. We just have to decide whether a customer should be suppressed or not for the next month base. Which technique can be used to solve this? We don't know what threshold to set for number of consecutive no conversions months....Can self learning/ Reinforcement learning be used here? Or sequential pattern mining? Rule based is my last option.
I could only find RL codes over the internet for games etc. If RL is to be used pls provide references.
Only tried rule based. Found the average thresholds based on historical data. For example if out of 10000 customers, 1000 converts. In those 1000 customers, 100 converts after getting recommended for 2 months, 500 for 3 months etc. Took the weighted average to find out the average number of months for the no conversion threshold to suppress a customer.
But this is the last and backup approach. Not backed by statistics.