Xi Chen

Bio: Xi Chen is an academic researcher from Nanjing University. The author has contributed to research in topics: Promotion (rank) & Sales promotion. The author has an hindex of 1, co-authored 6 publications receiving 18 citations.

Mining Social Lending Motivations for Loan Project Recommendations

Abstract: Online social lending has facilitated the ability of borrowers to reach lenders for financing support. With the increasing number of social lending projects, it is becoming very difficult for lenders to find appropriate projects to invest in, and for borrowers to get the funds they need. Project recommendation techniques provide a promising way to solve this problem to some degree, by recommending borrowers’ projects to lenders who are able to invest. Unfortunately, current loan project recommendations only explore some structured information to match borrowers and lenders, so they cannot achieve a satisfactory way to solve the problem very well. In this study, we innovatively mine a huge amount of unstructured data, the text data of borrowers’ and lenders’ motivations, to provide loan project recommendations that solve the problem of mismatches between borrowers and lenders. We present a motivation-based recommendation approach that uses text mining and classifier techniques to identify borrowers’ and lenders’ motivations. Using a dataset from the well-known social lending platform Kiva, our experiment results show that, compared with prior works, the proposed approach improves project recommendations in inactive lender groups and unpopular loan groups, which shows the superiority of the proposed approach in addressing data sparsity and cold start problems in loan project recommendations. This study thus initiates an attempt to solve the information overload problem and improve matching between borrowers and lenders through mining big unstructured text data found in a large number of P2P platforms.

Optimizing Two-Sided Promotion for Transportation Network Companies: A Structural Model with Conditional Bayesian Learning

Abstract: The mobile app of a transportation network company (TNC) has reshaped the taxi business model by providing new features and allowing the TNC platform to run a diverse two-sided sales promotion to help introduce those new features. We investigate the economic value of this app and how drivers build an initial preference for passenger matching, the cancellation feature, and online pay as well as how a two-sided sales promotion affects drivers’ willingness to use the TNC app. We estimate a structural model of drivers’ decisions to accept orders and to cancel generated orders and their perception of passengers’ willingness to utilize a sales promotion. Bayesian learning processes are introduced to account for drivers’ learning new features. We find evidence of the economic value of new features on a TNC app and drivers’ learning about the value of those features. Our results show that a platform subsidy and bids from passengers might signal low quality of service, and that platform cashback to passengers has a positive effect on drivers by increasing drivers’ chances of being rewarded. Our results further indicate that the substantial value of early promotion not only encourages current usage but also fosters learning that sustains drivers’ continued use of the app, and show how cashback for passengers affects the decisions of drivers. Finally, our policy simulations show improved performance with regard to drivers’ willingness to use the app as well as its cost effectiveness.

Optimizing Two-Sided Promotion for Transportation Network Companies: A Structural Model with Conditional Bayesian Learning

Abstract: The mobile app of a transportation network company (TNC) allows the TNC platform to run aggressive and diverse sales promotion to help introducing new product to two sides of users. This paper examines how two-sided sales promotion affects drivers’ willingness to use the TNC app and how the TNC forms its optimal promotion strategies accordingly. To investigate the effects of sales promotion, we estimate a structural model of drivers’ decisions of accepting orders and cancelling generated orders and their perception of passengers’ willingness to redeem sales promotion. Bayesian learning processes are introduced to account for decisions under uncertainty as the app is newly introduced. We find measurable evidence of taxi drivers’ learning about the attributes value of using transportation network app, indicating substantial value of promotion in early period since it not only encourages current usage, but also fosters learning that sustains drivers’ use afterwards. Our results also show that revealed tips from passengers signal low quality of orders, and platform cashback to passengers has positive effect on drivers by increasing drivers’ chances of being rewarded. Given the estimated parameters, we run simulations to explicitly measure indirect effects of sales promotion introduced by learning and show how cashback for passengers impacts the decisions of drivers. Finally, our experimental promotion policies show improved performance with regard to drivers’ willingness to use while being more cost effective.

The Role of Physical Stores in the Digital Age: Quasi-Experimental Evidence from Product Level Analysis

Abstract: With increasing ecommerce penetration, it is believed that consumers are spending more shopping time online and away from physical stores. This brings to question the role of physical stores in an increasingly digitized landscape and whether they remain relevant. The measurement of the impact of physical stores has been characterized by the difficulty of attributing the increase in online sales to customers seeing and experiencing products showcased in physical stores, as this information is not typically observed and captured. Should physical stores remain valuable in the digital age, which products should be showcased in stores? In this study, we attempt to shed light on these questions using a quasi-experiment, taking place through a nationwide retailer that expanded its physical presence during the study period. This work distinguishes from past studies in that it studies purchasing behavior in the underexplored Chinese market. Through a ``triple-differences'' framework, we provide a more direct evidence on the effect of the physical channel on online sales outcomes. We find that online sales for products showcased in physical stores increase for both high and low involvement products, suggesting that two possible mechanisms are at work in driving the online sales of showcased products.

Optimizing Two Sided Promotion for IS Enabled Transportation Network: A Conditional Bayesian Learning Model Completed Research Paper

Abstract: This paper investigates a typical two-sided micro-level business model of IS enabled transportation network. Specifically, we focus on how two-sided sales promotion interacts with users’ learning about attribute, and measure the effectiveness of sales promotion for their platform introductions. Our paper applies Bayesian learning model with an extension to account for multiple serial unobserved correlation. We find the measurable evidence of taxi driver’s learning about order commitment and payment methods of passenger. We furtherly identify that the attribute value of transportation network is undervalued in prior, which indicates that intensive promotion would not only attract user instantly, but also enhance user learning in long run. We name the effect on adoption rate driven by user learning as indirect effect of sales promotion. By running simulations, we quantify the indirect effect of sales promotion explicitly, and furtherly propose more efficient sales promotion strategy as managerial implication for industry.

Text Mining for Big Data Analysis in Financial Sector: A Literature Review

Abstract: Big data technologies have a strong impact on different industries, starting from the last decade, which continues nowadays, with the tendency to become omnipresent. The financial sector, as most of the other sectors, concentrated their operating activities mostly on structured data investigation. However, with the support of big data technologies, information stored in diverse sources of semi-structured and unstructured data could be harvested. Recent research and practice indicate that such information can be interesting for the decision-making process. Questions about how and to what extent research on data mining in the financial sector has developed and which tools are used for these purposes remains largely unexplored. This study aims to answer three research questions: (i) What is the intellectual core of the field? (ii) Which techniques are used in the financial sector for textual mining, especially in the era of the Internet, big data, and social media? (iii) Which data sources are the most often used for text mining in the financial sector, and for which purposes? In order to answer these questions, a qualitative analysis of literature is carried out using a systematic literature review, citation and co-citation analysis.

Business Models in the Sharing Economy: Manufacturing Durable Goods in the Presence of Peer-to-Peer Rental Markets

Abstract: With peer-to-peer sharing of durable goods like cars, boats, and condominiums, it is unclear how manufacturers should react. They could seek to encourage these markets or compete against them by of...

Multi-objective item evaluation for diverse as well as novel item recommendations

Abstract: Most of the traditional Recommendation Systems (RSs) focus on recommending only the popular items as they deal with a single objective precision/popularity. However, focusing on the diversity of the items in the recommendation list is also equally important to improve its relevance to the user, i.e., it is required to view RSs as a multi-objective optimization problem. Nevertheless, owing to popularity and diversity to be conflicting with each other, it degrades the accuracy of the recommendation list. Therefore, in this work, we use a multi-objective optimization method to maintain a trade-off between the popularity and the diversity and obtain multiple trade-off solutions in a single run. We first incorporate Bhattacharyya Coefficient in an existing nonlinear similarity computation model to create a new similarity model named as Bhat_sim to increase the prediction accuracy of the exiting rating evaluation methods. Further, we formulate a multi-parent crossover mechanism NewCross in the proposed multi-objective recommendation filtering NewCrossPMOEA which preserves the order and the frequency in the parents genes to bring good objectivity in the trade-off of recommending popular and diverse items in the recommendation list. The obtained results on the Movielens dataset demonstrate that the NewCrossPMOEA performs superior in terms of average precision, diversity, and novelty to its competing methods. Moreover, the Pareto-dominance concept of NewCrossPMOEA suggests multiple recommendation solutions of diverse and novel items to the target users in a single run.

Improving Credit Risk Prediction in Online Peer-to-Peer (P2P) Lending Using Feature selection with Deep learning

Abstract: At the early of 21st century, In the UK Peer2Peer (P2P) lending began with Zopa at the start of 2005. After that, it has grown rapidly in United States, China and some other countries. The main challenge for individual investors in the P2P lending market is to allocate their money efficiently through different loans by accurately evaluating the credit of each loan. The traditional ranking models cannot conform to the needs of individual investors in P2P lending because they do not provide natural mechanisms for asset allocation. P2P loans do not have the presence of traditional financial institutions. In this study, we propose a novel method for analyzing data for this emerging market. We have designed a credit risk model based on advanced machine learning methods, capable of assessing the returns and risks of individual loans. We also applied a selection feature method to eliminate the irrelevant features for improving the efficient of machine learning models. We conducted experiments on real-world data sets from P2P lending markets. The experimental results show that the proposed model can improve the efficiency of investment compared to the existing methods of P2P lending.