Recommending a model to forecast Sri Lanka wholesale price index using big data analytics

Abstract

The Whole Sale Price Index (WPI) is a main index, which is used to measure price variance before a product or service release to a consumer. WPI represents the basket of wholesale goods and services on market basket. Sri Lanka WPI is accumulated using Laspeyre's formula considering based year as 1974 and up till now not seasonally adjusted. Data collection, compilation, and Dissemination of WPI are done by Prices, Wedges, and Employment division of the Statistics Department of Central bank of Sri Lanka (CBSL) and releasing to public every month. Forecasting of WPI is necessary to understand the aid primary level economic impact of the country. Big data analysis and Data mining are using for data where it is hard to handle using traditional tools and techniques. Decision makers able to gain valuable insights analyzing that varied and rapidly changing data. Time series analysis compromise method for analyzing time series data in order to extract meaningful statistics and other characteristics of data. This review discusses the way to utilize big data analysis technology to systematically analyze time series based WPI data in Sri Lanka. The time series based forecast technologies ARIMA, ANN, VAR, Moving Average, AFARIMA etc. are reviewed based on previous findings. Based on the result will present the effective model to forecast WPIs in Sri Lanka and will critically evaluate selected WPIs. That selection will coordinate based on the weight and relationship to all items based WPI. WPI will compare with existing Sri Lankan Price Indices based on the relational factors.