The Author Online Book Forums are Moving

The Author Online Book Forums will soon redirect to Manning's liveBook and liveVideo. All book forum content will migrate to liveBook's discussion forum and all video forum content will migrate to liveVideo. Log in to liveBook or liveVideo with your Manning credentials to join the discussion!

Thank you for your engagement in the AoF over the years! We look forward to offering you a more enhanced forum experience.

HarleyGolfGuy (8) [Avatar] Offline
#1
Hi, this new book looks very interesting. I read the first chapter and at the end there is a nice table with the types of problems we can solve with machine learning. I am interested in using historical data in order to determine root cause, will this be covered at all in this book? It seems sort of like Imputation, the missing data being the root cause, but I'm not sure if it's the same thing.
henrik.brink (22) [Avatar] Offline
#2
Re: Machine Learning to determine root cause?
Without being an expert in root cause analysis, I would say the way to use machine learning for RCA is to build a classifier that can return the feature importance where the target is the particular (un)wanted event. E.g. the classifier returns a ranking of how important each feature was in the building of the model.

There are several algorithms that support this kind of model introspection, one of the more popular ones being Random Forest. In the upcoming chapter 3 and algorithm appendix, we will talk a bit about this.

Does that help?