Machine learning
Forecasting natural gas price trends using random forest and support vector machine classifiers
In this paper, different machine learning approaches are applied to forecasting future yearly price trends in the natural gas Title Transfer Facility market in the Netherlands.
Data and AI: addressing increasing regulation for smarter compliance
This webinar features leading compliance and risk management professionals and focuses on how firms can handle regulatory change management, fraud prevention, AML and other compliance needs through the use of an optimal data and AI foundation built for…
Neural networks show fewer false positives on bad loans – study
Machine learning method edges regression techniques in linking nonlinearities among delinquent borrowers
Fed: banks may need AI risk systems to cope with smart devices
Tenfold increase in web-enabled devices via 5G and IoT means explosion in cyber threats, says official
An ‘optimal’ way to calculate future P&L distributions?
Quants use neural networks to upgrade classic options pricing model
Machines say: ‘Ignore the spread in merger arb’
Closely watched arbitrage spread poor predictor of a merger deal’s success, quant firm finds
More banks flirt with machine learning for CCAR
Superior computational grunt of neural networks is attractive to lenders. Lack of explainability is the downside
Best AI and machine learning innovation: GBG
Asia Risk Awards 2021
Forecasting consumer credit recovery failure: classification approaches
This study proposes an advanced credit evaluation method for nonperforming consumer loans, which may serve as a new investment opportunity in the post-pandemic era.
Podcast: turbo-charging derivatives pricing
Quants achieve more speed by reducing number of dimensions in price calculations
A survey of machine learning in credit risk
This paper surveys the impressively broad range of machine learning methods and application areas for credit risk.
Comprehensive Capital Analysis and Review consistent yield curve stress testing: from Nelson–Siegel to machine learning
This paper develops different techniques for interpreting yield curve scenarios generated from the FRB’s annual CCAR review.
Axes that matter: PCA with a difference
Differential PCA is introduced to reduce the dimensionality in derivative pricing problems
Quant funds tackle chronic overfitting in crypto strategies
Firms adapt backtests and tread lightly to address “huge” overfitting risk, magnified by scarce data
Machines can read, but do they understand?
A novel NLP application built on a Google transformer model can help predict ratings transitions
Insider dealing: amping up surveillance measures
Joe Schifano, global head of regulatory affairs at Eventus, examines how volatility resulting from the Covid‑19 pandemic has made markets more susceptible to insider dealing activity, prompting regulators to urge firms to reinforce surveillance measures…
Podcast: NYU’s Kolm on transaction costs and machine learning
TCA methodologies that ignore partial fills “might be off by 20% to 30%”
NLP and transformer models for credit risk
News feeds are factored into models to predict credit events
AI helps one investor screen targets against UN ethical goals
PanAgora develops two-stage process that aims to weed out the greenwashers
An interpretable Comprehensive Capital Analysis and Review (CCAR) neural network model for portfolio loss forecasting and stress testing
This paper proposes an interpretable nonlinear neural network model that translates business regulatory requirements into model constraints.
Wells touts new explainability technique for AI credit models
Novel interpretability method could spur greater use of ReLU neural networks for credit scoring
Building forward-looking scenarios: why you’re doing it wrong
Rick Bookstaber and colleagues describe a process for constructing effective scenarios
Show your workings: lenders push to demystify AI models
Machine learning could help with loan decisions – but only if banks can explain how it works. And that’s not easy
Fast pricing of American options under variance gamma
This research develops a new fast and accurate approximation method, inspired by the quadratic approximation, to get rid of the time steps required in finite-difference and simulation methods, while reducing error by making use of a machine learning…