This paper examines how oil-price innovations affect the relative pricing of green and conventional-energy equity ETFs. Using daily data from January 2020 to October 2025, the principal Greenium is constructed as the difference between past-only rolling residual returns for the iShares Global Clean Energy ETF and the Energy Select Sector SPDR Fund, based on the Fama–French five-factor model augmented with momentum.Oil returns are strongly and negatively associated with the contemporaneous factor-adjusted Greenium. A 1% oil-price increase is associated with an approximately 23-basis-point decline in the rolling Greenium, with larger responses to positive than to negative oil shocks. The result is robust to alternative Greenium measures, predictor transformations, model ablations, moving-block permutation tests, and exclusion of the March–June 2020 episode. Strictly lagged models do not outperform the historical mean, indicating rapid same-day incorporation rather than next-day predictability. Student-t GARCH estimates reveal persistent volatility and substantial non-Gaussian downside risk. A parsimonious agent-based model combining persistent sustainability mandates with temporary oil-responsive reallocations improves weighted fit to local-projection responses by 23.4% relative to a direct-repricing benchmark. The evidence links energy shocks to short-run green–brown relative pricing without implying causal effects or changes in underlying sustainability preferences.
Financial time series are characterized by strong noise, frequent fluctuations, and dense local trend switching, making raw-sequence prediction difficult. This paper investigates stock time-series prediction from the perspective of pre-training sample construction and proposes Multi-step Trend Structure Extraction (MTSE). MTSE identifies local highs and lows in price and related indicator series under different step sizes and combinations, transforming continuous observations into trend-event representations. The occurrence and confirmation positions of events are distinguished, confirmed price-turning events are used as sample anchors, and the latest confirmed events in volume, RSI, and BIAS available before the decision point are aligned within a unified decision table. Using ChiNext Index data at one-minute, 15-minute, 60-minute, daily, and weekly frequencies, we compare a Raw sliding-window pipeline with an MTSE reconstruction pipeline under CatBoost, Transformer, and CNN models. Paired statistical tests, layered ablations, and net-of-cost backtesting are used for evaluation. The results show that MTSE changes sample size, label-switching frequency, and trend-segment organization. Relative to Raw inputs, MTSE improves F1, AUC, and MCC in most models and time granularities. Ablation results indicate that the gains are associated with the joint organization of event filtering, structural information, and multi-indicator alignment. In net-of-cost backtesting, the MTSE pipeline generally provides better risk–return profiles. These findings suggest that pre-training trend-structure reconstruction can improve model learning and financial usability in the ChiNext Index setting.
This study proposes a fraud detection framework for FinTech that integrates tabular deep learning with relational graph reasoning. We address a key limitation of state-of-the-art tabular fraud models: their assumption that transactions are independent, despite evidence that modern fraud often arises from coordinated infrastructure reuse (e.g., shared devices, email domains, accounts, and addresses). Using the IEEE-CIS Fraud Detection dataset (≈590,540 e-commerce transactions), we develop a hybrid architecture that combines TabNet, chosen for its built-in interpretability on tabular data, with a GraphSAGE encoder trained on a leakage-free heterogeneous entity graph constructed strictly from historical training transactions. Unseen entities in validation and test splits are mapped to dedicated unknown nodes, mirroring deployment conditions and preventing optimistic bias. Class imbalance is handled using square-root class weighting, avoiding synthetic oversampling methods that could distort real infrastructure topology. Empirically, the standalone TabNet baseline achieves ROC–AUC = 0.759 and PR–AUC = 0.149 on a forward-in-time test split. Incorporating relational learning via the proposed TabNet–GraphSAGE fusion improves performance to ROC–AUC = 0.791 and PR–AUC = 0.206, representing a 38% relative gain in PR–AUC and substantially enhancing minority fraud retrieval. The graph encoder alone attains meaningful predictive power, and ablation results confirm that the largest gains emerge from learned message passing and fusion, indicating complementarity between behavioural and infrastructural representations. Overall, results demonstrate that fraud detection is fundamentally a hybrid problem: combining local transaction anomalies with global relational structure yields more operationally relevant ranking quality and improved robustness in high-volume FinTech environments.
