消费价格指数(南非)
平均绝对百分比误差
物价指数
人工神经网络
粒子群优化
索引(排版)
膨胀(宇宙学)
可预测性
计算机科学
服装
计量经济学
统计
作者
Pradeepta Kumar Sarangi,Ashok Kumar Sahoo,Sachin Sinha
标识
DOI:10.1002/masy.202100349
摘要
The change in price of a group of goods and services is reflected in terms of consumer price index (CPI), making it one of the most important economic indicators. This is also the mostly used measure of inflation. Forecasted CPI values help the Government to take corrective measures to control the economic conditions of the country. This paper implements and examines two machine learning models such as artificial neural network (ANN) and ANN model optimized with particle swarm optimization (PSO) known as ANN-PSO to assess the accuracy in predictability of CPI. The data set for four groups such as food and beverages, housing, clothing, and footwear used for the calculation of all India CPI has been taken from the official website of the Government of India. The mean absolute percentage error (MAPE) has been used as the validator for model accuracy. The MAPE calculated for all experiments are less than 10% which indicates that the ANN-PSO models used are highly accurate for prediction of CPI of India.
科研通智能强力驱动
Strongly Powered by AbleSci AI