• Kovvuri Sindhuja
• S Durga Prasad

In today's farming, knowing how much crops will yield is really important to make the most out of the land, especially when the weather keeps changing. Old-fashioned ways of guessing aren't as reliable anymore, so farmers are turning to computer tricks like machine learning to help them out. This study is all about making those computer tricks even better by picking out the most important things from all the data we collect about the farm. Picking out the right stuff from all the data we collect is really important. It helps make sure the computer can do its job well without getting confused. We're using a smart tool called Boruta, which is like a really good guesser. It looks at all the data and figures out which parts are the most important for making predictions. It does this by playing around with the data in different ways until it finds the most useful bits. Another tool we're using is called Recursive Feature Elimination (RFE). It's a bit like going through a big list and picking out the best things. RFE is really careful and looks at each thing on the list to see if it's actually helpful. This way, we only keep the things that really matter for making good predictions. We're testing out different computer tricks, like Naive Bayes, Support Vector Machine (SVM), Logistic Regression, Decision Tree Classifier, K-Nearest Neighbor Classifier, and Random Forest Classifier. We want to see which ones work best for helping farmers predict how well their crops will do. This study is important because it helps farmers make better decisions about their crops. By using these smart computer tricks, we can make sure the predictions are accurate and easy to understand. This means farmers can plan better and make the most out of their farms even when the weather keeps changing.

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

"Enhancing Crop Yield Prediction Through Advanced Feature Selection Techniques and Ensemble Classifiers in Agricultural Environment Analysis ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.b550-b554, May-2024, Available :http://www.jetir.org/papers/JETIR2405166.pdf

"Enhancing Crop Yield Prediction Through Advanced Feature Selection Techniques and Ensemble Classifiers in Agricultural Environment Analysis ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppb550-b554, May-2024, Available at : http://www.jetir.org/papers/JETIR2405166.pdf