The copper industry faces challenges with skewed and noisy data in sales and pricing, which can hinder accurate manual predictions; a machine learning regression model can improve accuracy through techniques like normalization, feature scaling, and outlier detection.
Lead capture is another area of challenge, where a lead classification model can be used to predict customer conversion likelihood, classifying leads based on the ”STATUS” variable, with ”WON” as success and ”LOST” as failure.
By removing irrelevant data points and applying machine learning techniques, the copper industry can make better data-driven decisions for pricing and lead management.
By streamlit application user can modify the details and get the prediction as output
Technologies used in this project Streamlit — Python — Visual Studio — Library required in IDE
