{"id":1558,"date":"2019-03-07T01:35:57","date_gmt":"2019-03-07T01:35:57","guid":{"rendered":"http:\/\/kusuaks7\/?p=1163"},"modified":"2023-07-28T05:47:53","modified_gmt":"2023-07-28T05:47:53","slug":"scaling-machine-learning-from-0-to-millions-of-users-part-1","status":"publish","type":"post","link":"https:\/\/www.experfy.com\/blog\/ai-ml\/scaling-machine-learning-from-0-to-millions-of-users-part-1\/","title":{"rendered":"Scaling Machine Learning from 0 to Millions of Users\u200a\u2014\u200aPart 1"},"content":{"rendered":"
\n

I suppose most Machine Learning (ML) models are conceived on a whiteboard or a napkin, and born on a laptop. As the fledgling creatures start babbling their first predictions, we\u2019re filled with pride and high hopes for their future abilities. Alas, we know deep down in our heart that that not all of them will be successful, far from it.<\/p>\n

A small number fail us quickly as we build them. Others look promising, and demonstrate some level of predictive power. We are then faced with the grim challenge of deploying them in a production environment, where they\u2019ll either prove their legendary valour or die an inglorious death<\/p>\n

<\/canvas>
\u00a0<\/figcaption><\/figure>\n

One day, your models will rule the world\u2026 if you read all these posts and pay attention\u00a0\ud83d\ude09<\/span><\/p>\n

In this series of opinionated posts, we\u2019ll discuss\u00a0how to train ML models and deploy them to production, from humble beginnings to world domination<\/strong>. Along the way, we\u2019ll try to take justified and reasonable steps, fighting the evil forces of over-engineering, Hype Driven Development and \u201cwhy don\u2019t you just use XYZ?\u201d.<\/p>\n

Enjoy the safe comfort of your Data Science sandbox while you can, and prepare yourself for the cold, harsh world of production.<\/p><\/blockquote>\n

Day 0<\/strong><\/h3>\n

So you want to build a ML model. Hmmm. Let\u2019s pause for a minute and consider this:<\/p>\n