• Prerana R
• Shreya S Pai
• Yashaswini M
• Pradeep K R

Outlier detection in machine learning identifies events or actions that do not meet expectations of existing events in a dataset. These events can lead to various defects, frauds or errors. Outlier detection is an important issue that is researched in several research areas and also in various application domains [1]. Such values in an agriculture dataset may have effects on plant growth. So, outlier removal is an important process. Soybean being one of the most grown crops and even most asked crops in the world is contributing to 25% of world’s edible oil. Outliers present in the factors such as seed, leaves, stem, seed size, roots etc. may have hostile effects on plant growth of soybean crop. Hence detection of outliers in soybean crop growth becomes an important to achieve high yields. This allows the farmers to minimize yield losses taking correct actions when necessary. The proposed system uses machine learning techniques such as linear regression and Random Forest to find anomalies and remove them, thus increasing prediction accuracy of plant growth.

Outliers, Soybean, regression, classification

"Predictive Analysis of Soybean Crop Yield", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.86-89, April-2019, Available :http://www.jetir.org/papers/JETIR1904P15.pdf

"Predictive Analysis of Soybean Crop Yield", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp86-89, April-2019, Available at : http://www.jetir.org/papers/JETIR1904P15.pdf