The aim of this study is to demostrate that mobile phone usage data can be used to make predictions and find the best classification method for credit scoring even if the dataset is small (2,503 customers). We use different classification algorithms to split customers into paying and non-paying ones using mobile data, and then compare the predicted results with actual results. There are several related works publicly accessible in which mobile data has been used for credit scoring, but they are all based on a large dataset. Small companies are unable to use datasets as large as those used by these related papers, therefore these studies are of little use for them. In this paper we try to argue that there is value in mobile phone usage data for credit scoring even if the dataset is small. We found that with a dataset that consists of mobile data based only on 2,503 customers, we can predict credit risk. The best classification method gave us the result 0.62 AUC (area under the curve).
Reliable statistical information is important to make political decisions on a sound basis and to help measure the impact of policies. Unfortunately, statistics offices in developing countries have scarce resources and statistical censuses are therefore conducted sporadically. Based on mobile phone communications and history of airtime credit purchases, we estimate the relative income of individuals, the diversity and inequality of income, and an indicator for socioeconomic segregation for fine-grained regions of an African country. Our study shows how to use mobile phone datasets as a startin…
Globally, two billion people and more than half of the poorest adults do not use formal financial services. Consequently, there is increased emphasis on developing financial technology that can facilitate access to financial products for the unbanked. In this regard, smartphone-based microlending has emerged as a potential solution to enhance financial inclusion. We propose a methodology to improve the predictive performance of credit scoring models used by these applications. Our approach is composed of several steps, where we mostly focus on engineering appropriate features from the user dat…
An Experimental Study on Fairness-aware Machine Learning for Credit Scoring Problems
Banking Academy of Vietnam（越南银行学院）；Vietnam Academy of Science and Technology（越南科学技术 academy）；Hanoi University of Science and Technology（河内科学技术大学）；University of Koblenz（科隆大学）
Urban traffic systems worldwide are suffering from severe traffic safety problems. Traffic safety is affected by many complex factors, and heavily related to all drivers' behaviors involved in traffic system. Drivers with aggressive driving behaviors increase the risk of traffic accidents. In order to manage the safety level of traffic system, we propose Driving Safety Credit inspired by credit score in financial security field, and design a scoring method using trajectory data and violation records. First, we extract driving habits, aggressive driving behaviors and traffic violation behaviors…
University of California, Berkeley（加州大学伯克利分校）；Experian DataLabs LatAm（益博睿数据实验室拉丁美洲）；University of Sao Paulo（圣保罗大学）
We dissect an experimental credit scoring model developed with real data and demonstrate - without access to protected attributes - how the use of location information introduces racial bias. We analyze the tree gradient boosting model with the aid of a game-theoretic inspired machine learning explainability technique, counterfactual experiments and Brazilian census data. By exposing algorithmic racial bias explaining the trained machine learning model inner mechanisms, this experiment comprises an interesting artifact to aid the endeavor of theoretical understanding of the emergence of racial…
Reykjavik University（雷克雅未克大学）；University of Western Ontario（西安大略大学）；Grandata Labs（格兰达塔实验室）；KU Leuven（鲁汶大学）；University of Southampton（南安普顿大学）
Credit scoring is without a doubt one of the oldest applications of analytics. In recent years, a multitude of sophisticated classification techniques have been developed to improve the statistical performance of credit scoring models. Instead of focusing on the techniques themselves, this paper leverages alternative data sources to enhance both statistical and economic model performance. The study demonstrates how including call networks, in the context of positive credit information, as a new Big Data source has added value in terms of profit by applying a profit measure and profit-based fea…
Institute of Financial Service Analytics（金融服务分析研究所）；Alfred Lerner College of Business and Economics（阿尔弗雷德·勒纳商业与经济学院）；University Of Delaware（特拉华大学）
This paper examines two different yet related questions related to explainable AI (XAI) practices. Machine learning (ML) is increasingly important in financial services, such as pre-approval, credit underwriting, investments, and various front-end and back-end activities. Machine Learning can automatically detect non-linearities and interactions in training data, facilitating faster and more accurate credit decisions. However, machine learning models are opaque and hard to explain, which are critical elements needed for establishing a reliable technology. The study compares various machine lea…
This paper investigates the application of machine learning when training a credit decision model over real, publicly available data whilst accounting for "bias objectives". We use the term "bias objective" to describe the requirement that a trained model displays discriminatory bias against a given groups of individuals that doesn't exceed a prescribed level, where such level can be zero. This research presents an empirical study examining the tension between competing model training objectives which in all cases include one or more bias objectives. This work is motivated by the observation t…
Machine learning currently plays an increasingly important role in people's lives in areas such as credit scoring, auto-driving, disease diagnosing, and insurance quoting. However, in many of these areas, machine learning models have performed unfair behaviors against some sub-populations, such as some particular groups of race, sex, and age. These unfair behaviors can be on account of the pre-existing bias in the training dataset due to historical and social factors. In this paper, we focus on a real-world application of credit scoring and construct a fair prediction model by introducing late…
Recent studies have shown the value of mobile phone data to tackle problems related to economic development and humanitarian action. In this research, we assess the suitability of indicators derived from mobile phone data as a proxy for food security indicators. We compare the measures extracted from call detail records and airtime credit purchases to the results of a nationwide household survey conducted at the same time. Results show high correlations (> .8) between mobile phone data derived indicators and several relevant food security variables such as expenditure on food or vegetable cons…
Rappi（拉皮（ Rappi ））；Pontificia Universidad Católica del Perú（秘鲁天主教大学）；The University of Western Ontario（西安大略大学）
In this paper we present the impact of alternative data that originates from an app-based marketplace, in contrast to traditional bureau data, upon credit scoring models. These alternative data sources have shown themselves to be immensely powerful in predicting borrower behavior in segments traditionally underserved by banks and financial institutions. Our results, validated across two countries, show that these new sources of data are particularly useful for predicting financial behavior in low-wealth and young individuals, who are also the most likely to engage with alternative lenders. Fur…
