Prominent Technique for Rainfall Prediction using CatBoost over Light GBM for improving the Accuracy of Prediction
M. Uttej, L. Rama Parvathy · 2022
The purpose of this research is to assess the accuracy of rainfall prediction using the CatBoost and LightGBM algorithms. The classification technique is used for a rainfall dataset that has 145461 records. A paradigm for rainfall prediction that compares LightGBM with CatBoost has been suggested and built. The size of the sample was determined using G powers to be 10 within every cluster. The sample size was estimated using clinical evaluation, with alpha and beta values of 0.05 and 0.5, 95% assurance, and 80% from before the power. When it comes to forecasting amount of rain on large datasets, the CatBoost algorithm is 94.70% efficient, meanwhile the criteria-based LightGBM is 89.21% accurate. The significance level of CatBoost and LightGBM is p=0.003(p<0.05). Based on the results, the CatBoost beats the LightGBM in regards to precision.