For building any product, whether it includes ML or not, the first step is to identify the problem you're trying to solve. ML is a great tool for solving some problems, but there are many where it's best to start simpler. In this post, let's consider working for a company building a hypothetical product for automatically transcribing university lectures. We're going to build an automatic speech recognition (ASR) system which is tuned to work well for lectures -- this is something that definitely needs machine learning at its core. The product team have decided to start small and focus initially on just Physics lectures as a proof of concept.

Is your company or your team thinking of leveraging Machine Learning to build awesome products? In this second part*, intended to be a quick read, I have included the key take-aways from the panel discussion at the end of the event on the best practices and tips when building ML products. Please comment to this article if you don't agree with something or you want to share your experience o( ω)o In short, ML is not a silver bullet for everything (shiny technology phenomenon), there are the following considerations that the panel mentioned. If all above is yes, moving to tips on how to make the most of ML: You will need feedback mechanisms, so you can correct the data overtime. Organising and cleaning data efficiently will be key, but so will be integrating the feedback loop in your system.