The article explains how quality should be designed rather than merely measured, contrasts traditional QA with modern Quality Engineering, outlines the AI‑driven challenges and required metrics, and provides a concrete career roadmap for aspiring AI Quality Architects.
AlphaAgents introduces a role‑based multi‑agent framework—Fundamental, Sentiment, and Valuation agents—leveraging LLMs to analyze 10‑K reports, news, and price data, with a debate mechanism via Microsoft AutoGen; experiments on 15 tech stocks show superior cumulative returns and Sharpe ratios under risk‑neutral and risk‑averse settings compared to single‑agent baselines.
This article presents concise English summaries of four recent arXiv papers that explore AI-driven trading frameworks, dual‑view risk‑relation identification from 10‑K filings, multimodal language models for financial forecasting, and credit‑spread prediction enhanced by non‑financial data, highlighting their methods, datasets, and performance results.
A new AI system called Delphi-2M, built on an enhanced generative‑transformer architecture and trained with UK Biobank data, can forecast the risk of more than a thousand diseases up to twenty years in advance, achieving an average AUC of 0.67 in external validation while offering explainable, extensible predictions for personalized health.
Learn how to transform raw data into model-ready features through comprehensive preprocessing, variable derivation, dimensionality reduction, and the application of IV, PSI, and WOE metrics, with practical guidelines, thresholds, and visual examples to enhance risk model performance.
This article explains how Volcanic Engine safeguards the Model Context Protocol (MCP) throughout its lifecycle, detailing MCP fundamentals, core components, a step‑by‑step interaction example, seven major security risks, official design principles, and a comprehensive security architecture covering admission control, native design, and runtime protection.
This article presents a comprehensive overview of risk control model building for online small‑loan scenarios, covering pre‑loan, in‑loan and post‑loan stages, the associated data pipelines, model deployment strategies, optimization attempts, and monitoring frameworks to ensure accuracy, stability and effectiveness.
This article explains how to construct risk control feature portraits across four key scenarios—marketing, pre‑loan, in‑loan, and post‑loan—by selecting appropriate data dimensions, describing usable customer, behavior, and ID‑linked data, and illustrating each portrait with visual examples to guide accurate risk assessment.
This article presents a graph‑theory based mathematical model that treats nations as nodes and their relationships as weighted edges, using centrality metrics to quantitatively assess and forecast potential war risks, illustrated with a 2024 case study of key global regions and an adjacency matrix.
This article presents a comprehensive overview of using external data in consumer credit risk management, covering the risk operating framework, data types, challenges of data integration, evaluation methods, joint modeling techniques, and practical solutions to improve model performance and business outcomes.
This article presents 360 Shuke's practical approach to modeling low‑volume (tail) credit traffic using accumulated data, covering the characteristics of tail traffic, sample expansion under low approval rates, timeliness‑based data clustering, and ranking optimization for high‑quality head customers.
This article explores how graph machine learning can be leveraged for intelligent anti‑fraud, covering business background, common fraud models and graph algorithm principles, practical deployment of graph algorithms, challenges in fraud modeling, and future research directions.
This presentation explores how to scientifically define, apply, evaluate, and interpret data in financial risk management, covering data alignment with business goals, feature selection, model metrics such as KS and PSI, handling pandemic effects, and methods for model explainability.
This presentation explores how to scientifically define, apply, evaluate, and interpret data in financial risk management, covering data alignment with business goals, feature selection, model metrics like KS and PSI, handling pandemic impacts, and methods for model explanation and improvement.
This talk reviews the concept of alternative data, illustrates its early use in John Snow's cholera map, explores contemporary AI‑powered systems such as IBM's Debater and satellite‑based poverty estimation, and presents the speaker's own research on using unconventional data for financial‑market risk detection and prediction.
This article outlines G7's early-stage exploration of truck underwriting risk modeling, detailing data foundations, modeling objectives, key challenges such as target diversity and claim randomness, and proposes practical solutions across data sampling, feature engineering, model structure, and regionalization to improve risk assessment.
This article explains how Douyu leverages graph algorithms for live‑stream traffic anti‑cheat, detailing the platform’s risk scenarios, the overall graph architecture, its evolution, modeling workflow, practical case studies, and the resulting improvements in fraud detection and interpretability.
This article presents a comprehensive overview of credit risk control strategies, covering industry background, traditional scoring‑card development, data integration, feature engineering, model evaluation, rate and limit optimization, and advanced machine‑learning approaches for loan underwriting.
This article presents a comprehensive overview of financial big‑data risk control models at Du Xiaoman, covering traditional scoring cards, AI‑driven time‑series and text processing, graph‑based networks, model interpretability, probability calibration, stability analysis, and the specific challenges introduced by the COVID‑19 pandemic.
The article describes Ctrip's payment fraud risk characteristics, a comprehensive automated iterative anti‑fraud model framework—including variable system, GAN‑augmented sample generation, RNN behavior encoding, and tree‑based classifiers—and demonstrates how this approach restores recall performance compared with traditional static models.
This article presents a comprehensive overview of consumer credit risk management, covering industry background, traditional scoring‑card and machine‑learning model development processes, risk‑rate and limit strategies, rule effectiveness diagnostics, and advanced model‑optimization techniques to improve underwriting performance and cost efficiency.
This article presents a comprehensive workflow for group risk perception, covering business requirement mining, data acquisition and understanding, feature engineering, model training and evaluation, deployment, and practical user applications, with detailed objectives, methods, and deliverables for each stage.
This article introduces Auto Risk, a deep‑learning risk model for behavior‑sequence data that leverages unsupervised pre‑training with proxy tasks, details its convolution‑attention encoder, demonstrates significant gains across multiple business scenarios, and highlights its strong small‑sample and analogy capabilities.
This article introduces Auto Risk, a behavior‑sequence deep‑learning framework that uses unsupervised pre‑training with proxy tasks to learn universal feature representations from massive unlabeled data, achieving significant gains in risk‑control scenarios, improving AUC, supporting multi‑scene generalization and small‑sample learning.
The article compares traditional credit‑scoring‑card models with modern machine‑learning approaches for financial risk control, detailing feature selection criteria, non‑linear handling, data characteristics, practical ML techniques, large‑scale modeling challenges, and summarizing insights for future development.
This report details Ctrip Financial's end‑to‑end risk control development, covering business overview, a three‑layer data platform, the progression of credit scoring and anti‑fraud models from rule‑based to advanced AI techniques, and the evaluation, monitoring, and social‑network‑based fraud detection strategies employed.
This article explains how Alipay combats the surge of mobile payment fraud by upgrading its risk‑identification system with deep‑learning techniques, modeling victim and fraudster behavior sequences using LSTM, and integrating the resulting scores into existing models to achieve a measurable increase in detection coverage.
