A part of the reason for the discord between officers and the communities they serve is that they suspect many innocent people of guilt. Statistical models can help officers differentiate between the innocent and the guilty.

A part of the reason for the discord between officers and the communities they serve is that they suspect many innocent people of guilt. Statistical models can help officers differentiate between the innocent and the guilty.

Do you have a racist model on your hands? Here's how you can fix it.

Here, I examine a machine learning approach to labeling text with one of many labels.

There is not always enough data to train a model using supervised learning. In these cases, using an unsupervised model may be beneficial. In this blog post I show how a pre-trained word2vec model can be used for labeling text.