Seminar by QFRG & DSLab [27.11.2023]
We invite you to the thirty ninth seminar of the monthly series of meetings conducted jointly by QFRG (Quantitative Finance Research Group) and DSLab (Data Science Lab). The meeting will be devoted to the topic: Beyond Yelp – predicting restaurant closures based on Google Maps data, during which Tomasz Starakiewicz will talk about how to accurately predict restaurant bankruptcy using information available on Google Maps together with natural language processing tools and machine learning algorithms.
QFRG http://qfrg.wne.uw.edu.pl/ is a place where research is conducted and experiences are exchanged between people engaged in examining occurrences in the world of investment from the perspective of both theory and practice, on the verge of science and business.
The activity of DSLab http://dslab.wne.uw.edu.pl/ is focused mainly on academic projects devoted to deepening of the knowledge of DSLab team, sharing it with other people interested in Data Science issues and preparing scientific and didactic publications.
The meeting will take place on November 27th, 2023 (Monday) at 17:45 in online on Zoom.
Link to the meeting:
https://uw-edu-pl.zoom.us/j/97978554927?pwd=ZmorRmNDTThXWFhrV1JmODNWbG9udz09
The meeting will be conducted in English. The presentation is scheduled for about 45 minutes, and after that we invite you to a discussion.
Please log in the latest at 5:40 PM. The presentation will start at 5:45 PM.
Joining a meeting implies consent to recording. Please turn off cameras and microphones during the presentation and send the questions to the speaker in the chat.
Presentation abstract:
The restaurant sector is pivotal to firm exit research, influencing economic policy and managerial strategy recommendations. Recent studies using online data are based on geographically limited datasets and have largely omitted temporal dynamics in user interactions. Additionally, these studies rely on manual labeling for text analysis, a resource intensive approach. Our study introduces the first comprehensive, nationwide analysis of restaurant survival using Google Maps data. We analyze all Polish restaurants that have at least one review on google maps. The sample includes almost 41 thousand companies. We enhance the predictive performance of model by incorporating time-sensitive user interactions. Our model controls for established determinants of business exit and proves robust to data quality issues associated with user-provided business directories. We apply an efficient, label-free method for extracting semantic content from reviews, creating useful features for firm exit prediction. We apply a state-of-the-art xgboost algorithm and present an efficient feature selection strategy using hierarchical agglomerative clustering that retains predictive power while reducing model complexity. Our model has broad applications ranging from credit scoring to early-warning systems for business closures and presents a viable alternative to geographically constrained Yelp data.
