Learning how to build an recommendation system from initial signals

From a few initial adopters of a product, how we can target new set of users who are more likely can use the product

Building a targeting system to focus on building a score for users depending on early adopters

Git Repo : https://github.com/dinesh-coderepo/targetting-system

Recommendation systems and targeting systems

- recommendation systems suggest items to users by learning from their usage patterns and their picks. (own patterns extended to their their reco)
- targeting system is where there are few users who did a task, how can I identify who are high likely do that task
- We have cold start problem.