So, I have the customer purchase data in which customer_id, purchase_amount is available for multiple customers and for each month. These customers belong to same cluster i.e. their purchase pattern/items are same. Now I want to draw an single trend line using all customers data. Need an Machine Learning approach to solve this problem.
Data looks something like this
cust_id 2019-04-01 2019-05-01 2019-06-01 2019-07-01 2019-08-01
0 abc1 6143521.82 5664831.45 5996881.51 5016777.81 6518501.12
1 abc2 NaN NaN 5210911.66 4430187.66 4368016.60
2 abc4 3604093.99 3693334.39 4652815.13 4026998.99 NaN