From the course: Applied AI for Human Resources
Join today to access over 24,700 courses taught by industry experts.
Building an attrition model with Keras - Python Tutorial
From the course: Applied AI for Human Resources
Building an attrition model with Keras
- [Instructor] In this video, we will build an Attrition model with Keras. We start off by setting up the hyper parameters for the model. We will use an epoch of 100 and a batch size of 100. We will set verbose to one so that we can see the training results. The number of unique output classes is two. We will create hidden layers for 128 units. We will also do a validation split of 0.2. This means 20% of the data will be used for validation while building the model. I highly recommend experimenting with the hyper parameters to understand how they impact model accuracy. Now, we can create a Keras model. Then we add a dense, hidden layer with ReLU as activation. We then add a second hidden layer. Finally, we add an output dense layer with softmax activation. We compiled the model with Adam optimizer and use categorical crossentropy as the last function. We also measure the accuracy of the model. Then we fit the model for…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.