1 minute read

Next Steps

The dataset we identified has ~903.6k records. Based on our initial analysis, we identifed ~19% of the dataset contains NULL Values. So, we are planning to perform data cleaning, data pre-processing to check for Outliers, distributions etc. Based on the findings we will decide on the features that needs to be used for the models.THe anove mentioned steps are mostly the immediate next steps.

Overall, from the project perspective, we would be exploring different models, check for the RMSE errors. Pick the best performing model and check the predicted RMSE scores and report accordingly.