We propose an employee sentiment index, complementing investor sentiment and manager sentiment indices, and find that high employee sentiment predicts low monthly (weekly) market returns significantly both in- and out-of-sample. The predictability can also deliver sizable economic gains for...

The problem studied in this paper is a predigestion of the decision faced by online retailers (etailers) that advertise on publisher or comparison-shopping websites. An etailer may sell its product not only through its online and bricks-and-mortar stores, but also through the websites of one or...

The rise of smart and connected products has led to unprecedented data richness and the ever-increasing product connectivity, which catalyze the emergence of the data network effect and present a fresh opportunity for product innovation. This paper investigates whether and how connected product...

This study combines two streams of literature – text representation and machine learning-based causal inference, to study how to represent text as data to improve causal inference, i.e., estimating treatment effects more accurately. We choose a real problem context, Yelp reviews, to...

Ridesharing has become popular over the last decade, bringing significant changes to residents’ travel patterns and city traffic. Relevant to the growth and impact of ridesharing activities in populous urban areas are the side effects, such as air pollution and traffic congestion. Despite a...

In recent years, powder coatings are capturing more of the liquid coatings market due to their economical, ecological, environmental, and energy-saving benefits, yet their low surface qualities still hinder their wider application. In this study, ultrafine powder coatings (~ 20 µm in size) were...

Exploiting the intelligent stimuli-responsive fluorescent materials, which can selectively recognize lysozyme in fingerprints and enable high-contrast imaging, is still a challenge in detecting latent fingerprints (LFPs). Herein, aptamer functionalization and high-contrast reversible dual-color...

In this paper, we forecast Bitcoin's returns and return jumps using a self-exciting process embedded in a stochastic volatility model. We show the existence of the jump clustering feature, which varies depending on the frequency of the data. In an out-of-sample setting, we use a particle filter...