8 papers
Latent Laplace Diffusion for Irregular Multivariate Time Series
Zinuo You, Jin Zheng, John Cartlidge
Irregular multivariate time series impose a trade-off for long-horizon forecasting: discrete methods can distort temporal structure via re-gridding, while continuous-time models of…
StakeBench: Evaluating Language Understanding Grounded in Market Commitment
Yunhua Pei, Jingyu Hu, Yiwei Shi +3
Existing financial NLP benchmarks often rely on labels supplied by outside observers, measuring how language is perceived rather than what speakers have committed to in the market.…
Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems
Yunhua Pei, Zerui Ge, Jin Zheng +1
Multi-agent LLM decision systems for portfolio management still lack a principled way to assign credit across specialist agents, remain vulnerable to cold-start dominance under reg…
Contrast to Detect: Dynamic Graph Contrastive Regularization for Unsupervised Anomaly Detection in Multivariate Time Series
Yunhua Pei, Zixing Song, Jin Zheng +1
Anomaly detection in multivariate time series (MTS) is hindered by dynamic inter-variable dependencies and feature entanglement under spectral noise, and in practice, is further co…
A market-calibrated accelerated failure time model for in-play football forecasting
Lawrence Clegg, Zixing Song, John Cartlidge
In-play football forecasting models have struggled to match the accuracy of betting exchange prices, which aggregate information from many market participants. We close this gap by…
Enhancing Regime Shift Detection Using Unstructured Data: A Study on the Treasury Market
Mingxuan Yi, Vidal Mehra, Jing Chen +1
Regime shifts in financial markets reorganise the joint dynamics of asset prices and macro variables, breaking any single-regime calibration. They are nonetheless hard to identify:…
Automated Risk Management Mechanisms in DeFi Lending Protocols: A Crosschain Comparative Analysis of Aave and Compound
Erum Iftikhar, Wei Wei, John Cartlidge
Blockchain-based decentralised lending is a rapidly growing and evolving alternative to traditional lending, but it poses new risks. To mitigate these risks, lending protocols have…
zkMixer: A Configurable Zero-Knowledge Mixer with Anti-Money Laundering Consensus Protocols
Theodoros Constantinides, John Cartlidge
We introduce a zero-knowledge cryptocurrency mixer framework that allows groups of users to set up a mixing pool with configurable governance conditions, configurable deposit delay…