A NOVEL APPROACH OF SOCIAL MEDIA ANALYTICS FOR PREDICTING NATIONAL CONSUMER CONFIDENCE INDEX

Abstract

Consumer confidence captures the difference in consumer attitudes when making buying decisions. The consumer confidence index (CCI) is referenced by businesses, governments and other institutions when they make strategic decision. Analysis of Pakistani official consumer confidence index in comparison with the actual data reveals inconsistency between the official index and actual state of the economy in Pakistan. The data used in computing the official CCI has been collected using cross-sectional survey which has inherent limitations which spur research efforts to clarify and develop evidence on associations that form the core of the economic indicator of consumer confidence. It poses challenges to industry with regards to measuring the CCI as it is subjected to rigorous analysis. One aspect of such dynamic has to do with the emergence of new sources of digital data that could be used to measure consumer confidence. However, it is conjectured that using consumer sentiment data on social media might show greater marginal significance for consumer confidence, because the surveys might capture effects that will not appear in the data. Social media can offer a huge volume of data on consumer confidence, the analysis of which can be conducted at a more rapid time and can also refine the accuracy of the CCI using data from far larger populations. However, this study aims to propose a novel method of social media analytics for predicting national consumer confidence index (NACOP) that reflect true state of the economy. The proposed NACOP utilizes big data and data science to predict the national consumer confidence using large data sets of purchasing behaviour, jobs/employment, consumer price and personal finance from social media platforms. The study also explains the architecture of proposed NACOP and provides significant implications to academicians and practitioners.