The Use of Big Data and Its Effects in a Diffusion Forecasting Model for Korean Reverse Mortgage Subscribers

Jinah Yang,Daiki Min,Jeenyoung Kim

doi:10.3390/su12030979

Abstract

In recent years, big data has been widely used to understand consumers’ behavior and opinions. With this paper, we consider the use of big data and its effects in the problem of projecting the number of reverse mortgage subscribers in Korea. We analyzed web-news, blog post, and search traffic volumes associated with Korean reverse mortgages and integrated them into a Generalized Bass Model (GBM) as a part of the exogenous variables representing marketing effort. We particularly consider web-news volume as a proxy for marketer-generated content (MGC) and blog post and search traffic volumes as proxies for user-generated content (UGC). Empirical analysis provides some interesting findings: First, the GBM by incorporating big data is helpful for forecasting the sales of Korean reverse mortgages, and second, the UGC as an exogenous variable is more useful for predicting sales volume than the MGC. The UGC can explain consumers’ interest relatively well. Additional sensitivity analysis supports that the UGC is important for increasing sales volume. Finally, prediction performance is different between blog posts and search traffic volumes.

Highlights

The Bass diffusion model developed by Bass [1] has been widely used to explain the diffusion of new products or services in many areas
We showed that using big data improved prediction accuracy
We investigated whether big data can be used effectively to predict the sales of reverse mortgage (RM) in Korea by applying the Generalized Bass Model (GBM)

Summary

Introduction

The Bass diffusion model developed by Bass [1] has been widely used to explain the diffusion of new products or services in many areas. It attempts to explain innovations with external and internal influence. Product prices and advertising expenditures are the most typical examples of the exogenous variables [3,4,5,6]. These are meaningful for representing the effects of marketing efforts on attracting consumers, but they fail to closely reflect consumers’ internal interests. In the context of the GBM, we attempt to include variables that are likely to well represent consumers’ interests with the aims of improving the model’s prediction power

Objectives

Methods

Results

Conclusion