Scholarlink

This paper consolidates multivariate variables to offer a new approach to estimating the costs of handloom products. Data consisting of preprocessed handloom goods’ pricing, size, fabric type, colour, and design features were collected. Due to the highly intensive work characteristic of the handloom industry and its perceived cultural value, the latter struggles to establish appropriate prices mainly because of design density, fabrics used and colour options available. Therefore, the accurate prediction of prices is the best way to ensure the fairness of trades and the sustainability of crafts people’s lives. Based on these important variables, this study develops a forecast model of handloom prices by employing the Decision Tree Regression model which is a machine-learning technique. The stakeholders in the handloom organized sector can use the model because it reflects complex interrelationships of price and features with high accuracy. This research also shows that the integration of several features enhances the price forecast, thereby enabling the handloom market decision-makers to make the right decisions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimizing Handloom Price Prediction: Leveraging Diverse Features for Superior Accuracy Using Machine Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Khirod Chandra Maharana,
  • Binod Kumar,
  • Pravin Kumar,
  • Shrikant Upadhyay,
  • Binita Roshima Hinz

摘要

This paper consolidates multivariate variables to offer a new approach to estimating the costs of handloom products. Data consisting of preprocessed handloom goods’ pricing, size, fabric type, colour, and design features were collected. Due to the highly intensive work characteristic of the handloom industry and its perceived cultural value, the latter struggles to establish appropriate prices mainly because of design density, fabrics used and colour options available. Therefore, the accurate prediction of prices is the best way to ensure the fairness of trades and the sustainability of crafts people’s lives. Based on these important variables, this study develops a forecast model of handloom prices by employing the Decision Tree Regression model which is a machine-learning technique. The stakeholders in the handloom organized sector can use the model because it reflects complex interrelationships of price and features with high accuracy. This research also shows that the integration of several features enhances the price forecast, thereby enabling the handloom market decision-makers to make the right decisions.