Discovering patterns of customer financial behavior using social media data
- PDF / 1,715,205 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 48 Downloads / 287 Views
ORIGINAL ARTICLE
Discovering patterns of customer financial behavior using social media data Alexander Kalinin1 · Danila Vaganov1 · Klavdiya Bochenina1 Received: 25 March 2020 / Revised: 18 August 2020 / Accepted: 21 August 2020 © Springer-Verlag GmbH Austria, part of Springer Nature 2020
Abstract Social networks are a sterling source of information that reflects the real life of people in the digital space. This makes it possible to infer various aspects of the socioeconomic behavior of the user, even if he/she does not indicate them explicitly. In this study, on the one hand, we consider Russian online social network VK.com, which is analog to the global Facebook platform. On the other hand, there is a supplementary financial information source provided by the bank company. Combining the data of online social media with debit card transactions, we train machine learning models to infer the socioeconomic status (SES) of the user, as well as six purchasing patterns that characterize customer transactional activity of certain type. Namely, we detect if a user is a driver, parent, gamer, traveler, or he/she prefers to purchase at night/in the morning. SES is defined as average monthly expenses and considered as real number variable. The following features are extracted as predictors: demographic information from a user’s page, user participation in communities, topics of that communities, text embeddings of user posts, topological characteristics, and graph embeddings of nodes in the friendship graph. Obtained results show the superiority of graph embeddings in both classification and regression tasks (median absolute percentage error MedAPE = 29.7 for SES). Moreover, for drivers (Macro-F1 = 0.688 ) and parents (Macro-F1 = 0.679 ), the higher scores are reached by concatenation of different features. In addition, we investigate feature importance values and found that topics of user communities and the structure of its network influence on the model stronger than other features. The performed study shows the power of online social media data for inferring user socioeconomic attributes. Keywords Online social media · Socioeconomic status · Purchasing patterns · Attribute inference · Graph embeddings
1 Introduction The development of the Internet facilitates the transition of people to a digital space where information spreads extremely faster. Every day, users of social networks and online markets are looking for products and services. On the one hand, recommendation systems and personalized advertising help the user to reduce search time, and, on the other, bring benefits to online platforms. To generate suitable recommendations and advertising, the system needs
* Alexander Kalinin [email protected] Danila Vaganov [email protected] Klavdiya Bochenina [email protected] 1
ITMO University, Saint‑Petersburg, Russia
user attributes, which are often missing. Attribute inference has been extensively studied. In the case of social networks, researchers tried to infer age (Sloan et al. 2015; Zhang et al. 2016
Data Loading...
