Data Analytics platforms, with predictive models at their core, are the buzzword in Enterprise Analytics. Having been on both sides - a consultant providing analytics and a consumer of analytics, I’ve realized that there are few, if any, runaway winners. Rightly so. It is one of the hottest growth areas. This talk would go over some of the ingredients to building successful machine learning algorithms for the data analytics platform using Python. It is probably easy to build a simplistic machine learning model. But what does it take to build reasonably good, or even better - a state-of-art, model? What is the impact on the design/architecture of the data science components when data scales? Is there a secret sauce? When data scales, what are the trade-offs to consider? How far can one go when expert domain knowledge is not available in-house ? Based on learnings and results from actual business use cases, the talk would try to answer those above questions, along with the constraints various choices impose when creating the platform - when using Python stack. There will be emphasis on the following with actual results: Feature engineering, modeling selection, ensembling, importance of bias-variance and generalization. Expected Background of Audience: Anyone with an interest in analytics.