# q-fin.RM Published articles for q-fin.RM. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## CADENCE: Distributional Next-Transaction Forecasting for Business Cash-Flow Underwriting DevFeed: [CADENCE: Distributional Next-Transaction Forecasting for Business Cash-Flow Underwriting]() Original publisher: [Read original article]() Author: Alexander Wu, Jingchao Huang Published: 2026-10-30T04:00:00Z Content type: article Language: en Sources: [arXiv: Machine Learning]() Topics: [Neural Network](), [fourier transform]() Tags: [abstract](), [applications](), [approval-rate](), [business](), [cadence](), [calendar](), [cash-flow](), [cs-lg](), [distribution](), [embedding](), [evaluation](), [event](), [fft](), [forecasting](), [models](), [network](), [payment](), [production](), [q-fin-rm](), [semantics](), [small-business](), [transaction]() ### AI overview CADENCE forecasts the amount and a nonparametric timing distribution of each cash flow's next payment using a compact causal Transformer that treats transactions as tokens. It combines transaction semantics from an external labeler and frozen text encoder with calendar inputs and no-event supervision. Ablations attribute short-history recall gains to counterparty semantics, timing accuracy to calendar inputs, and precision to no-event supervision. Against the production FFT baseline, CADENCE improves one-day timing accuracy by 93.3% and next-event F1 by 6.7%. In production application evaluations, replacing FFT recurrence features with CADENCE features raises KS by 4.8%, increases approval rate by 18.2% at fixed loss, and lowers loss rate by 13.1% at fixed approval. These are reported results from the abstract; it does not provide methodological detail or broader validation. ### Source excerpt arXiv:2610.38084v1 Announce Type: new Abstract: Recurring cash flows are the backbone of cash-flow underwriting: they separate durable revenue from one-off deposits, expose standing obligations, and ultimately determine ability to pay. For small businesses, recurrence is both indispensable and hard to estimate, because much of their income arrives as ambiguous transfers, most payment streams are short, and schedules follow calendar conventions that frequency-domain methods treat as noise. We present CADENCE, Calendar-Aware Distributional Event Network for Cash-Flow Estimation, a compact causal Transformer that treats each transaction as a token and predicts the amount and a full, nonparametric timing distribution of every cash flow's next payment. Inheriting transaction semantics from an external labeler and a frozen text encoder keeps CADENCE compact yet general across the long tail of small-business counterparties, while predicting a calibrated distribution rather than an opaque embedding makes its outputs interpretable enough to feed existing underwriting models and power credit decisions. Ablations confirm the role of each design choice, with counterparty semantics driving recall on short histories, calendar inputs driving timing accuracy, and no-event supervision driving precision. Against the production FFT baseline, CADENCE improves one-day timing accuracy by 93.3% and next-event F1 by 6.7%, while producing calibrated distributions that serve directly as a confidence gate for downstream decisions. In an end-to-end credit evaluation on production applications, replacing FFT recurrence features with CADENCE features raises KS by 4.8%, raises the approval rate at a fixed loss rate by 18.2%, and lowers the loss rate at a fixed approval rate by 13.1%. ## Deep catastrophic-risk-aware reinforcement learning DevFeed: [Deep catastrophic-risk-aware reinforcement learning]() Original publisher: [Read original article]() Author: Carlos P\\'erez Octavio Mendoza, Fr\\'ed\\'eric Godin Published: 2026-10-21T04:00:00Z Content type: article Language: en Sources: [arXiv: Machine Learning]() Topics: [Reinforcement learning](), [Deep learning](), [Neural Network]() Tags: [automatic](), [cs-lg](), [deep](), [experiment](), [method-of-moments](), [neural](), [optimization](), [q-fin-rm](), [reinforcement-learning](), [risk](), [theory](), [training]() ### AI overview The paper applies Extreme Value Theory (EVT) to train neural-network policies for Conditional Value-at-Risk (CVaR) when extreme-risk observations are scarce. It models exceedances above a selected threshold using a peaks-over-threshold representation and method-of-moments estimation, yielding a differentiable tail-risk objective whose finite-sample gradient can be computed by automatic differentiation, conditional on that threshold. After validation in a controlled experiment, the authors compare EVT- and empirical-CVaR-trained policies in deep hedging: behavior is similar under normal conditions, while EVT-trained policies have lower hedging losses in extreme-scenario evaluation across the training sample sizes tested. These abstract-level results suggest EVT may be a practical alternative in this setting; they do not establish performance beyond the reported experiments. ### Source excerpt arXiv:2610.27214v1 Announce Type: new Abstract: Estimating extreme risk in reinforcement learning becomes increasingly difficult as the confidence level increases, since only a small number of observations contribute to empirical estimates of Conditional Value-at-Risk (CVaR). In this paper, we extend an Extreme Value Theory (EVT) approach for CVaR optimization to high-dimensional neural-network policies. Using a peaks-over-threshold representation and method-of-moments estimation, we obtain a differentiable tail-risk objective and show that, conditional on the selected threshold, its finite-sample gradient can be computed directly through automatic differentiation. We first validate the approach in a controlled experiment with a known optimal solution and then investigate its performance in a deep-hedging problem with rare extreme market movements. Our results show similar hedging behavior for EVT- and empirical-CVaR-trained policies under normal conditions, while EVT-trained policies exhibit lower hedging losses under the extreme-scenario evaluation across the training sample sizes considered. These results suggest that EVT can provide a practical alternative for training neural policies when the observations relevant to extreme risk are scarce. ## The Control Layer Behind Rule-Following Agents Trading Across Market Conditions DevFeed: [The Control Layer Behind Rule-Following Agents Trading Across Market Conditions]() Original publisher: [Read original article]() Author: Saad Naja, Nasser Odtallah, Jake Van-Praag, Sarah May Published: 2026-10-21T04:00:00Z Content type: article Language: en Sources: [arXiv: Artificial Intelligence](), [arXiv: Machine Learning]() Topics: [google-adk](), [test](), [reproducibility](), [audit]() Tags: [agent-evaluation](), [agents](), [ai](), [ai-trading](), [ai-trading-agents](), [cs-ai](), [cs-lg](), [cs-ma](), [evaluation](), [q-fin-rm](), [q-fin-tr](), [risk](), [rules](), [strategies](), [strategy](), [test](), [tests](), [toolkit](), [trade](), [trading]() ### AI overview Across 2,627 closed positions from February to August 2026, four AI trading agents showed high adherence to declared strategies and risk rules, even though one was unprofitable. Most positions were simulated against live prices with a 0.09% round-trip fee; 18% used real Hyperliquid orders. Agents kept 97.5% of gross losses within declared stops, and 23 of 24 runs respected the five-position limit. Profitability tracked win frequency relative to each strategy's break-even rate, while the same market data produced different results under different strategies. The study offers rerunnable trade-log tests and regime tests requiring published Bitcoin prices and regime labels. These are trade-level findings, not account-level returns or proof of a lasting edge; the authors present discipline as a necessary but insufficient test before allocating capital. ### Source excerpt arXiv:2610.26324v1 Announce Type: cross Abstract: Trading discipline often fails people. Our study tested whether four AI trading agents followed their strategies and risk rules. Offering traders the evidence and an agent evaluation toolkit to separate luck from following the rules, before giving agents meaningful autonomy or capital. Our study analysed 2,627 closed positions from 12 February to 27 August 2026 across the same asset universe and execution conditions. Most positions were simulated against live prices with a 0.09% round-trip fee; 18% involved real Hyperliquid orders. Each position declared a strategy, stop and target, with a limit of five open positions per agent. The fleet finished net positive after fees. Rule adherence was high across all four agents, including the unprofitable one. Profitability tracked how often agents won relative to their break-even win rates. Institutional-style controls ran by default and contained losses through a 29% market drawdown and recovery, with documented exceptions. The discipline held for all four agents. Agents kept 97.5% of gross loss within declared stops, and typical losses closed at declared levels. Declared risk remained stable after losses and broadly stable across calm and volatile months. Twenty-three of 24 runs respected the position limit; logs identify the exception's size and duration. The same live data produced different results across assigned strategies. The trade-log tests can be rerun from the published trade snapshot; regime tests also require the published Bitcoin prices and regime labels. Section 3.5 specifies the stop-breach tolerance. These trade-level results are not account-level returns or proof of a lasting edge. Our study provides an evaluation toolkit to help traders distinguish rule-following from luck before committing capital. For anyone considering allocating capital to agents to trade, discipline should be the entry test, not the only test. ## Conditional Weight of Evidence for Gradient-Boosted Credit Models: Estimation, Additivity and Its Relation to Adverse Action Reasons DevFeed: [Conditional Weight of Evidence for Gradient-Boosted Credit Models: Estimation, Additivity and Its Relation to Adverse Action Reasons]() Original publisher: [Read original article]() Author: Agus Sudjianto, Denis Burakov Published: 2026-10-21T04:00:00Z Content type: article Language: en Sources: [arXiv: Machine Learning]() Topics: [Machine learning](), [Predictive AI]() Tags: [conditional](), [cs-lg](), [gradient-boosted-trees](), [machine-learning](), [q-fin-rm](), [stat-me](), [stat-ml]() ### AI overview Conditional weight of evidence measures how a credit characteristic changes an applicant's default log odds after the other known credit information is taken into account; its sign and magnitude indicate whether, and how strongly, it adds adverse or favorable information. The same characteristic value can therefore carry different evidence for applicants with different records. In a bureau-style simulation, regressions on a full gradient-boosted model's predicted probabilities recover conditional evidence more accurately than separate outcome models when the full model is accurate. They also recover a constructed file-age effect that varies with utilization and is often missed by marginal weight of evidence. Local class-frequency estimates improve on marginal estimates but remain inaccurate for some weak effects. A FICO HELOC application illustrates estimation when population evidence is unknown. The authors distinguish both applicant-specific conditional evidence and its population summary, conditional information value, from adverse action reasons: neither explains the fitted score difference between an applicant and selected passing records. ### Source excerpt arXiv:2610.24586v1 Announce Type: cross Abstract: Traditional weight of evidence assigns a credit characteristic a value based on its association with default across a population. Credit analysis also requires an assessment of that characteristic in the context of an individual applicant's record. We study conditional weight of evidence for this purpose. It measures the change in default log odds from observing a characteristic after the remaining credit information is known. Its sign identifies whether the characteristic adds adverse or favorable information for that applicant, and its magnitude measures the strength of that information. The same characteristic value can therefore receive different assessments for applicants with different payment histories or other credit attributes. We develop estimators using gradient-boosted trees and evaluate their accuracy in a bureau-style simulation. Regressions of the full model's predicted probabilities recover conditional evidence more accurately than separate models fitted to default outcomes, provided the full model is accurate. They also recover a deliberately constructed file-age effect whose direction varies with utilization and is often missed by marginal weight of evidence. Local class-frequency estimates improve on marginal weight of evidence but remain inaccurate for some weak effects. An application to FICO HELOC data illustrates estimation when the population evidence is unknown. Conditional weight of evidence provides an applicant-specific interpretation of the information in a credit characteristic; its population summary, a conditional information value, splits the joint information in the record across blocks when averaged over orderings. Neither is an adverse action reason, which explains the fitted score difference between the applicant and chosen passing records.