• Ch Sowjanya
• K. Subhash Chandra
• K. Subhash Chandra

predicting crop yields is an important task in agriculture, a dynamic area that is heavily influenced by environmental factors including precipitation, humidity, and temperature. Historically, farmers had to rely on trial and error when determining when to plant seeds, how often to check on their crops, and when to harvest. Traditional methods, however, are being tested by a shifting ecological landscape. Recently, machine learning methods have been incorporated to help with forecasting duties. In order to forecast future harvests, this investigation employs a number of machine learning strategies. Selecting pertinent characteristics that turn raw data into a suitable structure for computation is crucial for maximising the efficacy of machine learning models. Feature selection eliminates superfluous information and hones in on crucial details to make a more precise model. The complexity of the model-building process can be reduced by carefully picking the most relevant elements, as emphasised in this article. It also shows how extra time and space are needed to store and process irrelevant features, which can reduce model accuracy. The research shows that compared to the standard classification method, the prediction accuracy of an ensemble method is higher

Crop prediction, machine learning, feature selection, classification, ensemble technique.

"Crop prediction accuracy by considering a comprehensive set of features and leveraging advanced feature selection techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 10, page no.f114-f118, October-2023, Available :http://www.jetir.org/papers/JETIR2310513.pdf

"Crop prediction accuracy by considering a comprehensive set of features and leveraging advanced feature selection techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 10, page no. ppf114-f118, October-2023, Available at : http://www.jetir.org/papers/JETIR2310513.pdf