Helpfulness of online reviews plays an important role in customer purchase decision making process. However, the review helpfulness prediction problem is considered to be quite challenging and hard. This paper aims to explore this problem and build a helpfulness pre-
diction model. Our model utilizes a rich set of features based on textual content of reviews, meta-data of reviews and characteristics of reviewers. The proposed predictive model is validated using six real-life review datasets and the experimental results are found to be
quite promising. Our experimental analysis of the impact of product type such as search and experience goods on review helpfulness also reveals interesting insights.