I'll think of something clever

In the previous post we introduced the problem, which was to learn to classify the fashionMNIST dataset by Zalando and made some steps toward the best solution by introducing the Neural Networks which already strikingly overperformed a traditional machine learning algorithm. Here, we will take it a step further. CNN We will move to another model, Convolutional Neural Networks (or CNN). This model is way fitter to process images as its structure acknowledges the context we’re operating with and is therefore stronger at detecting visual patterns than a simple neural network.

In the previous posts we decided to take a dataset and explore it, analyse it and create good visualization that would highlight its patterns and peculiarities. Then we took even further and decided to make use of some well-known machine learning algorithm to tackle the problem of being able to predict a specific target feature on new instances. We found those algorithm to perform remarkably well on such datas, coming close to perfection prediction-wise.

Goal In the previous post we explored a dataset of 14999 employers data in an hypothetical company seeking to understand a pattern behind employees leaving said company. We analyzed the data, studied it and visualized many charts in hope to understand some of the underlying patterns. In this post, our goal will be to train a Machine Learning algorithm to solve the company’s problem and be able to predict whether an employee is likely to quit his job in the foreseeable future.

Data is fascinating. To me, it’s no surprise that we are moving toward an ever-increasing production of data, to the point that each day in our life we (and even our everyday tools) produce and consume huge amounts of data. This data describes our world, from our everyday life to our bank account, from the railway system of a region to the economic movements of entire nations. It’s huge, and it’s getting huger with every seconds that goes by.