Predictive Modeling with Big Data: Is Bigger Really Better?

  • Enric Junqué de Fortuny
  • David Martens
  • Foster Provost

With the increasingly widespread collection and processing of “big data,” there is natural interest in using these data assets to improve decision making.  One of the best understood ways to use data to improve decision making is via predictive analytics.  An important, open question is: to what extent do larger data actually lead to better predictive models?  In this article we empirically demonstrate that when predictive models are built from sparse, fine-grained data—such as data on low-level human behavior—we continue to see marginal increases in predictive performance even to very large scale.  The empirical results are based on data drawn from nine different predictive modeling applications, from book reviews to banking transactions.  This study provides a clear illustration that larger data indeed can be more valuable assets for predictive analytics.  This implies that institutions with larger data assets—plus the skill to take advantage of them—potentially can obtain substantial competitive advantage over institutions without such access or skill.  Moreover, the results suggest that it is worthwhile for companies with access to such fine-grained data, in the context of a key predictive task, to gather both more data instances and more possible data features.  As an additional contribution, we introduce an implementation of the multivariate Bernoulli Naïve Bayes algorithm that can scale to massive, sparse data.