SocialCredit+ is AI powered credit scoring system that leverages publicly available social media data to augment traditional credit evaluation. It uses a conversational banking assistant to gather user consent and fetch public profiles. Multimodal feature extractors analyze posts, bios, images, and friend networks to generate a rich behavioral profile. A specialized Sharia-compliance layer flags any non-halal indicators and prohibited financial behavior based on Islamic ethics. The platform employs a retrieval-augmented generation module: an LLM accesses a domain specific knowledge base to generate clear, text-based explanations for each decision. We describe the end-to-end architecture and data flow, the models used, and system infrastructure. Synthetic scenarios illustrate how social signals translate into credit-score factors. This paper emphasizes conceptual novelty, compliance mechanisms, and practical impact, targeting AI researchers, fintech practitioners, ethical banking jurists, and investors.
Performative prediction models account for feedback loops in decision-making processes where predictions influence future data distributions. While existing work largely assumes insensitivity of data distributions to small strategy changes, this assumption usually fails in real-world competitive (i.e. multi-agent) settings. For example, in Bertrand-type competitions, a small reduction in one firm's price can lead that firm to capture the entire demand, while all others sharply lose all of their customers. We study a representative setting of multi-agent performative prediction in which insensitivity assumptions do not hold, and investigate the convergence of natural dynamics. To do so, we focus on a specific game that we call the ''Bank Game'', where two lenders compete over interest rates and credit score thresholds. Consumers act similarly as to in a Bertrand Competition, with each consumer selecting the firm with the lowest interest rate that they are eligible for based on the firms' credit thresholds. Our analysis characterizes the equilibria of this game and demonstrates that when both firms use a common and natural no-regret learning dynamic -- exponential weights -- with proper initialization, the dynamics always converge to stable outcomes despite the general-sum structure. Notably, our setting admits multiple stable equilibria, with convergence dependent on initial conditions. We also provide theoretical convergence results in the stochastic case when the utility matrix is not fully known, but each learner can observe sufficiently many samples of consumers at each time step to estimate it, showing robustness to slight mis-specifications. Finally, we provide experimental results that validate our theoretical findings.
In contemporary economic society, credit scores are crucial for every participant. A robust credit evaluation system is essential for the profitability of core businesses such as credit cards, loans, and investments for commercial banks and the financial sector. This paper combines high-performance models like XGBoost and LightGBM, already widely used in modern banking systems, with the powerful TabNet model. We have developed a potent model capable of accurately determining credit score levels by integrating Random Forest, XGBoost, and TabNet, and through the stacking technique in ensemble modeling. This approach surpasses the limitations of single models and significantly advances the precise credit score prediction. In the following sections, we will explain the techniques we used and thoroughly validate our approach by comprehensively comparing a series of metrics such as Precision, Recall, F1, and AUC. By integrating Random Forest, XGBoost, and with the TabNet deep learning architecture, these models complement each other, demonstrating exceptionally strong overall performance.
Credit scores are critical for allocating consumer debt in the United States, yet little evidence is available on their performance. We benchmark a widely used credit score against a machine learning model of consumer default and find significant misclassification of borrowers, especially those with low scores. Our model improves predictive accuracy for young, low-income, and minority groups due to its superior performance with low quality data, resulting in a gain in standing for these populations. Our findings suggest that improving credit scoring performance could lead to more equitable access to credit.
There is a tight connection between credit access and voting. We show that uncertainty in access to credit pushes voters toward more conservative candidates in US elections. Using a 1% sample of the US population with valid credit reports, we relate access to credit to voting outcomes in all county-by-congressional districts over the period 2004-2016. Specifically, we construct exogenous measures of uncertainty to credit access, i.e. credit score values around which individual total credit amount jumps the most (e.g. around which uncertainty on access to credit is the highest). We then show that a 10pp increase in the share of marginal voters located just around these thresholds increases republican votes by 2.7pp, and reduces that of democrats by 2.6pp. Furthermore, winning candidates in more uncertain constituencies tend to follow a more conservative rhetoric.
This paper investigates gaps in access to and the cost of housing credit by race and ethnicity using the near universe of U.S. mortgage applications. Our data contain borrower creditworthiness variables that have historically been absent from industry-wide application data and that are likely to affect application approval and loan pricing. We find large unconditional disparities in approval and pricing between racial and ethnic groups. After conditioning on key elements of observable borrower creditworthiness, these disparities are smaller but remain economically meaningful. Sensitivity analysis indicates that omitted factors as predictive of approval/pricing and race/ethnicity as credit score can explain some of the pricing disparities but cannot explain the approval disparities. Taken together, our results suggest that credit score, income, and down payment requirements significantly contribute to disparities in mortgage access and affordability but that other systemic barriers are also responsible for a large share of disparate outcomes in the mortgage market.
Explainable Artificial Intelligence is a concept aimed at making complex algorithms transparent to users through a uniform solution. Researchers have highlighted the importance of integrating domain specific contexts to develop explanations tailored to end users. In this study, we focus on the Schufa housing scoring system in Germany and investigate how users information needs and expectations for explanations vary based on their roles. Using the speculative design approach, we asked business information students to imagine user interfaces that provide housing credit score explanations from the perspectives of both tenants and landlords. Our preliminary findings suggest that although there are general needs that apply to all users, there are also conflicting needs that depend on the practical realities of their roles and how credit scores affect them. We contribute to Human centered XAI research by proposing future research directions that examine users explanatory needs considering their roles and agencies.
Soft default, defined as a delinquency of 90 days or more, is a relatively common event in the credit market, in 2010 such episodes affected about 3 million individuals. Yet we lack a detailed understanding of what happens afterward. We use credit report data, on approximately 2 million individuals from 2004 to 2020, to shed light on individual trajectories after such event, and document enduring negative impacts. These effects persist for up to ten years post-event and manifest in lower credit scores, reduced total credit limits, lower homeownership rates, lower income, and relocation to less economically active zip codes. It appears that those who are overextended in their mortgage lines, and with larger delinquent amounts, suffer the harshest consequences.
When a customer overdraws their bank account and their balance is negative they are assessed an overdraft fee. Americans pay approximately \$15 billion in unnecessary overdraft fees a year, often in \$35 increments; users of the Mint personal finance app pay approximately \$250 million in fees a year in particular. These overdraft fees are an excessive financial burden and lead to cascading overdraft fees trapping customers in financial hardship. To address this problem, we have created an ML-driven overdraft early warning system (ODEWS) that assesses a customer's risk of overdrafting within the next week using their banking and transaction data in the Mint app. At-risk customers are sent an alert so they can take steps to avoid the fee, ultimately changing their behavior and financial habits. The system deployed resulted in a \$3 million savings in overdraft fees for Mint customers compared to a control group. Moreover, the methodology outlined here is part of a greater effort to provide ML-driven personalized financial advice to help our members know, grow, and protect their net worth, ultimately, achieving their financial goals.
In order to track and comprehend the academic achievement of students, both private and public educational institutions devote a significant amount of resources and labour. One of the difficult issues that institutes deal with on a regular basis is understanding the exam shortcomings of students. The performance of a student is influenced by a variety of factors, including attendance, attentiveness in class, understanding of concepts taught, the teachers ability to deliver the material effectively, timely completion of home assignments, and the concern of parents and teachers for guiding the student through the learning process. We propose a data driven approach that makes use of Machine Learning techniques to generate a classifier called credit score that helps to comprehend the learning journeys of students and identify activities that lead to subpar performances. This would make it easier for educators and institute management to create guidelines for system development to increase productivity. The proposal to use credit score as progress indicator is well suited to be used in a Learning Management System. In this article, we demonstrate the proof of the concept under simplified assumptions using simulated data.
Although many fairness criteria have been proposed to ensure that machine learning algorithms do not exhibit or amplify our existing social biases, these algorithms are trained on datasets that can themselves be statistically biased. In this paper, we investigate the robustness of a number of existing (demographic) fairness criteria when the algorithm is trained on biased data. We consider two forms of dataset bias: errors by prior decision makers in the labeling process, and errors in measurement of the features of disadvantaged individuals. We analytically show that some constraints (such as Demographic Parity) can remain robust when facing certain statistical biases, while others (such as Equalized Odds) are significantly violated if trained on biased data. We also analyze the sensitivity of these criteria and the decision maker's utility to biases. We provide numerical experiments based on three real-world datasets (the FICO, Adult, and German credit score datasets) supporting our analytical findings. Our findings present an additional guideline for choosing among existing fairness criteria, or for proposing new criteria, when available datasets may be biased.
Digital loans have exploded in popularity across low and middle income countries, providing short term, high interest credit via mobile phones. This paper reports the results of a randomized evaluation of a digital loan product in Nigeria. Being randomly approved for digital credit (irrespective of credit score) substantially increases subjective well-being after an average of three months. For those who are approved, being randomly offered larger loans has an insignificant effect. Neither treatment significantly impacts other measures of welfare. We rule out large short-term impacts either positive or negative: on income and expenditures, resilience, and women's economic empowerment.
Realistically -- and equitably -- modeling the dynamics of group-level disparities in machine learning remains an open problem. In particular, we desire models that do not suppose inherent differences between artificial groups of people -- but rather endogenize disparities by appeal to unequal initial conditions of insular subpopulations. In this paper, agents each have a real-valued feature $X$ (e.g., credit score) informed by a "true" binary label $Y$ representing qualification (e.g., for a loan). Each agent alternately (1) receives a binary classification label $\hat{Y}$ (e.g., loan approval) from a Bayes-optimal machine learning classifier observing $X$ and (2) may update their qualification $Y$ by imitating successful strategies (e.g., seek a raise) within an isolated group $G$ of agents to which they belong. We consider the disparity of qualification rates $\Pr(Y=1)$ between different groups and how this disparity changes subject to a sequence of Bayes-optimal classifiers repeatedly retrained on the global population. We model the evolving qualification rates of each subpopulation (group) using the replicator equation, which derives from a class of imitation processes. We show that differences in qualification rates between subpopulations can persist indefinitely for a set of non-trivial equilibrium states due to uniformed classifier deployments, even when groups are identical in all aspects except initial qualification densities. We next simulate the effects of commonly proposed fairness interventions on this dynamical system along with a new feedback control mechanism capable of permanently eliminating group-level qualification rate disparities. We conclude by discussing the limitations of our model and findings and by outlining potential future work.
The paper investigates the effects of the credit market development on the labor mobility between the informal and formal labor sectors. In the case of Russia, due to the absence of a credit score system, a formal lender may set a credit limit based on the verified amount of income. To get a loan, an informal worker must first formalize his or her income (switch to a formal job), and then apply for a loan. To show this mechanism, the RLMS data was utilized, and the empirical method is the dynamic multinomial logit model of employment. The empirical results show that a relaxation of credit constraints increases the probability of transition from an informal to a formal job, and improved CMA (by one standard deviation) increases the chances of informal sector workers to formalize by 5.4 ppt. These results are robust in different specifications of the model. Policy simulations show strong support for a reduction in informal employment in response to better CMA in credit-constrained communities.
The granting process of all credit institutions rejects applicants who seem risky regarding the repayment of their debt. A credit score is calculated and associated with a cut-off value beneath which an applicant is rejected. Developing a new score implies having a learning dataset in which the response variable good/bad borrower is known, so that rejects are de facto excluded from the learning process. We first introduce the context and some useful notations. Then we formalize if this particular sampling has consequences on the score's relevance. Finally, we elaborate on methods that use not-financed clients' characteristics and conclude that none of these methods are satisfactory in practice using data from Cr\'edit Agricole Consumer Finance. ----- Un syst\`eme d'octroi de cr\'edit peut refuser des demandes de pr\^et jug\'ees trop risqu\'ees. Au sein de ce syst\`eme, le score de cr\'edit fournit une valeur mesurant un risque de d\'efaut, valeur qui est compar\'ee \`a un seuil d'acceptabilit\'e. Ce score est construit exclusivement sur des donn\'ees de clients financ\'es, contenant en particulier l'information `bon ou mauvais payeur', alors qu'il est par la suite appliqu\'e \`a l'ensemble des demandes. Un tel score est-il statistiquement pertinent ? Dans cette note, nous pr\'ecisons et formalisons cette question et \'etudions l'effet de l'absence des non-financ\'es sur les scores \'elabor\'es. Nous pr\'esentons ensuite des m\'ethodes pour r\'eint\'egrer les non-financ\'es et concluons sur leur inefficacit\'e en pratique, \`a partir de donn\'ees issues de Cr\'edit Agricole Consumer Finance.
Online leading has disrupted the traditional consumer banking sector with more effective loan processing. Risk prediction and monitoring is critical for the success of the business model. Traditional credit score models fall short in applying big data technology in building risk model. In this manuscript, data with various format and size were collected from public website, third-parties and assembled with client's loan application information data. Ensemble machine learning models, random forest model and XGBoost model, were built and trained with the historical transaction data and subsequently tested with separate data. XGBoost model shows higher K-S value, suggesting better classification capability in this task. Top 10 important features from the two models suggest external data such as zhimaScore, multi-platform stacking loans information, and social network information are important factors in predicting loan default probability.
In [1], we have explored the theoretical aspects of feature selection and evolutionary algorithms. In this chapter, we focus on optimization algorithms for enhancing data analytic process, i.e., we propose to explore applications of nature-inspired algorithms in data science. Feature selection optimization is a hybrid approach leveraging feature selection techniques and evolutionary algorithms process to optimize the selected features. Prior works solve this problem iteratively to converge to an optimal feature subset. Feature selection optimization is a non-specific domain approach. Data scientists mainly attempt to find an advanced way to analyze data n with high computational efficiency and low time complexity, leading to efficient data analytics. Thus, by increasing generated/measured/sensed data from various sources, analysis, manipulation and illustration of data grow exponentially. Due to the large scale data sets, Curse of dimensionality (CoD) is one of the NP-hard problems in data science. Hence, several efforts have been focused on leveraging evolutionary algorithms (EAs) to address the complex issues in large scale data analytics problems. Dimension reduction, together with EAs, lends itself to solve CoD and solve complex problems, in terms of time complexity, efficiently. In this chapter, we first provide a brief overview of previous studies that focused on solving CoD using feature extraction optimization process. We then discuss practical examples of research studies are successfully tackled some application domains, such as image processing, sentiment analysis, network traffics / anomalies analysis, credit score analysis and other benchmark functions/data sets analysis.
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 from driver's trajectories and traffic violation records. Next, we train a classification model to filtered out irrelevant features. And at last, we score each driver with selected features. We verify our proposed scoring method using 40 days of traffic simulation, and proves the effectiveness of our scoring method.
Machine learning models are increasingly used to automate decisions that affect humans - deciding who should receive a loan, a job interview, or a social service. In such applications, a person should have the ability to change the decision of a model. When a person is denied a loan by a credit score, for example, they should be able to alter its input variables in a way that guarantees approval. Otherwise, they will be denied the loan as long as the model is deployed. More importantly, they will lack the ability to influence a decision that affects their livelihood. In this paper, we frame these issues in terms of recourse, which we define as the ability of a person to change the decision of a model by altering actionable input variables (e.g., income vs. age or marital status). We present integer programming tools to ensure recourse in linear classification problems without interfering in model development. We demonstrate how our tools can inform stakeholders through experiments on credit scoring problems. Our results show that recourse can be significantly affected by standard practices in model development, and motivate the need to evaluate recourse in practice.