Kraken is primarily a platform built for data analysts or business analysts without a deep understanding of data science. As such, we try to automate as much of the data science work as we can and do not currently support more expert level features like hyper parameter tuning.
Articles in this section
- How does Kraken choose algorithms?
- What algorithms does Kraken use to train models?
- What is the "Score" Kraken produces in the Analysis Results?
- What pre-processing is done to my data prior to training a model?
- Can I tune the hyper parameters of the model?
- How is the model trained and tested? Why doesn’t my model completely match the historical data?
- How can I improve my model score?
- What is “overfitting”? Why is it generally better to use a smaller number of Drivers in my model?