Handling Unseen Categories in Label Encoding for SKU Column in Predictive Sales Model

Apr 30, 2024, 12:29 AM

Train a XGBoost model based on the train csv to predict the total number of sales of the result.csv. Try to find the model that would perform best for this

Now that we have cleaned both the training and result datasets, we can proceed to preprocess the data for model training. This includes converting categorical data to numerical format, handling missing values if any, and splitting the data into features and labels. After preprocessing, we will train a XGBoost model to predict the total number of sales.
Get started with Vizly