Assessing influence of online reputation on sales using a zero-inflated negative binomial model

作者：Min Xu; Qiang Ye; Xiaolin Wang; Mohan Wang

来源：Procedia Computer Science, 2017, 122: 1108-1113.

DOI：10.1016/j.procs.2017.11.480

• Reputation
• Sales volume
• Count data
• Zero-inflated negative binomial model

Seller Reputation in online platform plays a vital role in consumer purchasing decisions. Many researchers explore the impact of reputation on sales; however, the majority of them consider sales as continuous variable. We in this paper will treat it as count data and focus on how reputation influence sales volume. Taking into account excess zeros and over-dispersion characteristics of sales, we build a zero-inflated negative binomial (ZINB) model to address the issue. We find that reputation will have two types of influences. The results show that reputation will influence both the amount of sales and the probability that sellers always have no sales.

• 出版日期2017
• 单位西南大学