I'm trying to automate retrain steps of our ML models. My aim is hyper-parameter tuning with current data (newer performance window) using same algorithm and features on production environment. Imagine that it works periodically (like once per 6 months) and tries to beat the eval result of the model in prod environment. It will uses same feature set and algorithm (i.e. XGBClassifier). We can give hyper-parameter values of prod ML model initially.
I'm stuck on how can i define a search space over hyper-parameters automatically? Code may be capitalized on initial HP values. But how to set it automatically?
