On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,694 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “Super-App”

Supporting Financial Inclusion with Graph Machine Learning and Super-App Alternative Datacs.LG

Graph machine learning and Super-App data improve credit risk prediction for financial inclusion.

problem Improving credit risk prediction for financial inclusion.

method Two graph-based experiments using centrality, behavior, and transactionality features.

result Graph features enhance credit risk models, leading to more inclusive financial systems.

Graph machine learning Super-Apps Credit risk Financial inclusion Centrality

2021-02-19abs ↗pdf ↗

Enhancing User' s Income Estimation with Super-App Alternative Datacs.LG

Paper uses Super-App data to improve income estimation models.

problem Improving accuracy of income estimation models.

method TreeSHAP method for Stochastic Gradient Boosting Interpretation.

result Alternative data from Super-Apps capture more information than traditional financial data.

income estimation Super-Apps alternative data TreeSHAP behavioral patterns

2021-04-12abs ↗pdf ↗

Relational Graph Neural Networks for Fraud Detection in a Super-App environmentcs.LG

Relational Graph Neural Networks improve fraud detection in Super-Apps.

problem Fraud detection in Super-Apps using alternative data.

method Relational Graph Convolutional Networks applied to heterogeneous graphs.

result Added value in fraud detection when considering alternative data and interactions.

fraud detection Super-App graph neural networks heterogeneous graphs interpretability

2021-07-29abs ↗pdf ↗

Optimizing Credit Limit Adjustments Under Adversarial Goals Using Reinforcement Learningq-fin.GN

Study uses RL to optimize credit card limits, achieving better results than traditional methods.

problem Optimizing credit card limit adjustments in banking.

method Reinforcement learning with offline learning strategy.

result Double Q-learning agent outperforms other strategies in generating optimal policy.

Reinforcement Learning Credit Limit Optimization Banking Adversarial Goals Super-app Data

2023-06-27abs ↗pdf ↗

Super-App Behavioral Patterns in Credit Risk Models: Financial, Statistical and Regulatory Implicationsq-fin.GN

Alternative app data improves credit scoring for underserved borrowers.

problem Improving credit scoring for low-wealth and young individuals.

method Use of alternative data from app-based marketplaces, validated with TreeSHAP method.

result Alternative data sources predict financial behavior better than traditional bureau data.

credit scoring alternative data app-based marketplaces TreeSHAP underbanked

2020-05-09abs ↗pdf ↗