A Cosine Similarity–Based Framework for Plant Recommendation Using Indian Agro- Climatic and Soil Data

Authors

  • Suman Das Assistant Professor, Department of MCA, Techno College Hooghly, Chinsurah, India
  • Anik Patra Assistant Professor, Department of MCA, Techno College Hooghly, Chinsurah, India
  • Aniket Basu Student, Department of MCA, Techno College Hooghly, Chinsurah, India.
  • Subhankar Nath Student, Department of MCA, Techno College Hooghly, Chinsurah, India.
  • Md Salman Student, Department of MCA, Techno College Hooghly, Chinsurah, India.

DOI:

https://doi.org/10.65525/prabandhan.v1i2.8

Keywords:

Recommendation System, Cosine Similarity, Smart Gardening, E-commerce, Machine Learning

Abstract

A recommendation system is a filtering tool designed to predict the compatibility of items for users. In this study, the domain-specific items were plants suited to Indian regions. The Plant Recommendation System provides a list of recommended plants based on user-provided zip codes and environmental conditions such as temperature, humidity, sunlight, and rainfall. The system classifies India into six soil types and eleven zones and collects data on thirty plant species, each annotated with minimum/maximum temperature ranges, average rainfall, humidity, and sunlight needs. Cosine similarity was used to match the user inputs with the plant feature vectors. In addition to recommendations, users can add items to a wish list, add to cart, and complete a checkout process through integrated e-commerce features. The system fetches real-time location and weather data using third-party APIs. Drawbacks include a limited plant database and reliance on cosine similarity; future work will expand plant data, employ hybrid recommendation methods, and integrate IoT-based sensors for automated gardening.

Downloads

Published

2025-11-26

How to Cite

Das, S., Patra, A., Basu, A., Nath, S., & Salman, M. (2025). A Cosine Similarity–Based Framework for Plant Recommendation Using Indian Agro- Climatic and Soil Data . Prabandhan Darpan - Journal of Management Studies, 1(2), 21–29. https://doi.org/10.65525/prabandhan.v1i2.8