The Joint Diffusion of a Digital Platform and its Complementary Goods: The Effects of Product Ratings and Observational Learning

TL;DR

This study models the joint diffusion of an OSS platform and its complements, highlighting how ratings, observational learning, and governance influence adoption and competition among platforms.

Contribution

It extends the Bass Diffusion Model with a novel EKF-MCMC estimation approach to analyze OSS platform and complement adoption dynamics.

Findings

Ratings and observational learning boost add-on demand

Add-ons expand the platform's market potential

Slow review processes hinder platform success

Abstract

The authors study the interdependent diffusion of an open source software (OSS) platform and its software complements. They quantify the role of OSS governance, quality signals such as product ratings, observational learning, and user actions upon adoption. To do so they extend the Bass Diffusion Model and apply it to a unique data set of 6 years of daily downloads of the Firefox browser and 52 of its add-ons. The study then re-casts the resulting differential equations into non-linear, discrete-time, state space forms; and estimate them using an MCMC approach to the Extended Kalman Filtern (EKF-MCMC). Unlike continuous-time filters, the EKF-MCMC approach avoids numerical integration, and so is more computational efficient, given the length of our time-series, high dimension of our state space and need to model heterogeneity. Results show, for example, that observational learning and add-on ratings increase the demand for Firefox add-ons; add-ons can increase the market potential of the Firefox platform; a slow add-on review process can diminish platform success; and OSS platforms (i.e. Chrome and Firefox) compete rather than complement each other.