FARM MANAGEMENT AND ACCOUNTING (KEY IJP************342)

• Mansi F. Nagpure,Rutuja B. Janbandhu,Asst. Prof. Abhijeet. A. Thakare

Abstract

ABSTRACT The farm management and accounting is an Machine Learning model in which an individual will the analysis of market overview and prediction of crop that are supposed to harvest in particular area. The project is further modeled on existing available data from last 8 years the data might be variable. The Crop Survival model is an innovative application of machine learning designed to revolutionize agricultural practices by providing precise insights into crop viability and market trends. Leveraging data from the past eight years, this model harnesses the power of historical agricultural data to predict crop survival rates and forecast market dynamics for specific regions. Keywords: Machine Learning, Crop Prediction, Decision Tree , SVM, Rainfall Prediction, Crop Recommendation.1. INTRODUCTION The farm management and accounting is a Machine Learning model in which an individual will the analysis of market overview and prediction of crop that are supposed to harvest in particular area. At its core, the Crop Survival model utilizes a diverse range of variables collected over the years, encompassing factors such as weather patterns, soil quality, irrigation methods, pest infestation rates, and socioeconomic indicators. By analyzing this rich dataset, the model can generate accurate predictions regarding which crops are most likely to thrive in a given area during a particular season. One of the key strengths of the Crop Survival model lies in its adaptability to variable conditions. Agricultural ecosystems are inherently dynamic, influenced by numerous unpredictable factors such as climate change, economic fluctuations, and technological advancements. Therefore, the model continuously learns and evolves, incorporating new data and refining its algorithms to stay relevant and effective in changing environments. Moreover, the Crop Survival model not only aids farmers in making informed decisions about crop selection but also serves as a valuable tool for policymakers, agricultural researchers, and market analysts. By providing comprehensive insights into crop survival probabilities and market trends, this model facilitates strategic planning, resource allocation, and risk management across the agricultural sector.The crop price prediction and cultivation guidance aims to provide farmers with accurate market insights by predicting future crop prices for each specific market. This proactive approach enables farmers to enhance their revenue by making informed crop selection decisions. Additionally, the system includes a cultivation guidance feature that simplifies the farming experience by offering crop status tracking and relevant guidance throughout the cultivation process. To implement this feature, we collect and analyze various data sets, including historical crop prices, rainfall patterns, demand and supply data, and cultivation process information. Using machine learning algorithms, such as Random Forest, Logistic Regression, and Decision Tree, we determine the best-fit algorithm to meet our project requirements. The data is stored in a MongoDB cluster, and fetching methods from the React JS library are used to retrieve the data in the front end. The virtual farm creation process involves storing farmersinformation, including their crop and land data, and analyzing the most suitable cultivation processes. The system provides comprehensive status tracking of crops throughout their growth stages. To utilize the system, farmers input details such as the crop name, district for market selection, and date for prediction. This data is then processed by the prediction engine, which generates the most probable result value. By automating the market study process for farmers, this system eliminates the need for manual research. It offers an efficient and reliable solution for farmers to make well-informed decisions, ultimately improving their farming practices and overall outcomes.