DailyChunks

  training : access to  training data  and  testing (holdout) data . was there sampling of any kind applied to create this dataset? are we introducing any data leaks? production : access to  batches  or  real-time  streams of ML content from various sources how can we trust that this stream only has data that is consistent with what we have historically seen? Assumption Reality Reason All of our incoming data is only machine learning related (no spam). We would need a filter to remove spam content that's not ML related. To simplify our ML task, we will assume all the data is ML content. Our task Labeling Our task Labels : categories of machine learning (for simplification, we've restricted the label space to the following tags:  natural-language-processing ,  computer-vision ,  mlops  and  other ). Features : text features (title and description) that describe the content. Assumption Reality Reason Content can only belong ...

  Background Set the scene for what we're trying to do through a user-centric approach: users : profile/persona of our users goals : our users' main goals pains : obstacles preventing our users from achieving their goals Value proposition Propose the value we can create through a product-centric approach: product : what needs to be built to help our users reach their goals? alleviates : how will the product reduce pains? advantages : how will the product create gains? Objectives Breakdown the product into key objectives that we want to focus on. Solution Describe the solution required to meet our objectives, including its: core   features : key features that will be developed. integration : how the product will integrate with other services. alternatives : alternative solutions that we should considered. constraints : limitations that we need to be aware of. out - of - scope . : features that we will not be developing for now. Feasibility How feasible is our solution and do we...