From chatbots to research workflows
Our agentic work evaluates whether AI can search, synthesize and forecast—not simply answer isolated prompts.
Academic Research · AI, Finance & Empirical Science
Building AI that can reason about finance—and improve how research itself is done.
Selected AIDF and collaborative research spans live multi-agent financial forecasting, deep-document research, trustworthy retrieval, blockchain graph intelligence, human-behavior foundation models, multimodal scientific reasoning, synthetic stress testing and AI-native empirical methods. The common theme is simple: frontier AI should not only predict better; it should reason over complex systems, produce evidence, withstand scrutiny and make scientific conclusions more reliable.
Research philosophyWe focus on questions where conventional predictive modeling is not enough—because the AI must search, reason, verify, understand structure or improve the validity of the measurement and inference process.
AIDF research signal map
AI × Finance
× ScienceResearch Core
× ScienceResearch Core
Agentic AI
Trustworthy AI
Forecasting
Scientific AI
Graph & Blockchain
Behavior & Multimodal
22AI / CS conference papersSelected research across leading venues
7Journal papersSelected top and field-leading outlets
10+Leading AI / CS venuesNeurIPS · ICLR · ICML · EMNLP · ACL · KDD · WWW · SIGMOD · ICDE · ACM MM
7Research clustersFrom agents to graphs, behavior and scientific AI
Research programs
A portfolio organised around difficult research problems—not around one algorithm.
The map below shows the recurring research programs behind the publication portfolio. Select a theme to see what it is trying to solve.
AIDF
Research
Research
01 / AGENTIC FINANCIAL INTELLIGENCE
Agentic Financial Intelligence
Agents that search, reason, collaborate and execute multi-step financial research workflows.
4 selected papers in this research cluster
AI conferences first
Selected AI & computer-science conference research
These papers span frontier AI, data systems and computational research infrastructure—from LLM agents and financial benchmarks to blockchain graphs, behavior foundation models and multimodal scientific reasoning. Each summary is written for a broad audience, and every card links to Google Scholar.
Selected journal research
AI-enhanced empirical methods, organizations and networks
The journal portfolio complements the conference work with durable research on AI-enabled empirical methods, decentralized-finance risk, networks and the consequences of AI for work: how to correct bias, build valid variables, control confounding and understand complex digital systems.
Why this research matters
Research that travels between academia and real financial systems.
The academic portfolio is intentionally built around problems that matter in both worlds: autonomous research, evidence quality, model reliability, market forecasting, blockchain intelligence, human behavior and the statistical validity of AI-generated information.
Failure modes become measurable
Hallucination, retrieval drift and weak financial reasoning are turned into benchmarkable research problems.
Markets are graphs, not flat tables
Blockchain and exchange research models dynamic transaction structure, fraud, routing and arbitrage as connected systems.
AI should understand people—and improve inference
Behavior models, machine-generated measures, textual confounding and missing data all require stronger scientific safeguards.