Purpose

This study identifies whether the Internet search index can be used as effective enough data to identify agricultural and livestock product demand and compare the accuracy of the prediction of major agricultural and livestock products purchases between these prediction models using artificial neural network, linear regression and a decision tree.

Design/methodology/approach

Artificial neural network, linear regression and decision tree algorithms were used in this study to compare the accuracy of the prediction of major agricultural and livestock products purchases. The analysis data were studied using 10-fold cross validation.

Findings

First, the importance of the Internet search index among the 20 explanatory variables was found to be high for most items, so the Internet search index can be used as a variable to explain agricultural and livestock products purchases. Second, as a result of comparing the accuracy of the prediction of six agricultural and livestock purchases using three models, beef was the most predictable, followed by radishes, chicken, Chinese cabbage, garlic and dried peppers, and by model, a decision tree shows the highest accuracy of prediction, followed by linear regression and an artificial neural network.

Originality/value

This study is meaningful in that it analyzes the purchase of agricultural and livestock products using data from actual consumers' purchases of agricultural and livestock products. In addition, the use of data mining techniques and Internet search index in the analysis of agricultural and livestock purchases contributes to improving the accuracy and efficiency of agricultural and livestock purchase predictions.

中文翻译：

---

使用互联网搜索索引和数据挖掘技术预测农畜产品采购

目的

本研究确定互联网搜索指数是否可以作为足够有效的数据来识别农畜产品需求，并使用人工神经网络、线性回归和决策比较这些预测模型之间主要农畜产品采购的预测准确性。树。

设计/方法/方法

本研究采用人工神经网络、线性回归和决策树算法，比较主要农畜产品采购预测的准确性。使用 10 倍交叉验证研究分析数据。

发现

首先，互联网搜索指数在20个解释变量中的重要性被发现对大多数项目来说都很高，因此互联网搜索指数可以作为解释农畜产品购买的变量。其次，通过三种模型对六种农牧业采购的预测准确度进行比较，牛肉是最可预测的，其次是萝卜、鸡肉、大白菜、大蒜和干辣椒，根据模型，决策树显示预测精度最高，其次是线性回归和人工神经网络。

原创性/价值

本研究的意义在于利用消费者实际购买农畜产品的数据来分析农畜产品的购买情况。此外，在农畜采购分析中使用数据挖掘技术和互联网搜索索引有助于提高农畜采购预测的准确性和效率。