Artificial intelligence
Managing AML and fraud – A risky business needs a risk-based approach
Financial services organisations (FSOs) are expected to meet strict financial crime regulations regardless of their size, and those with smaller budgets and fewer resources are finding this increasingly difficult as regulations, guidelines and threats…
Driving anti-money laundering efficiency gains using artificial intelligence
Anti-money laundering (AML) is expensive and labour-intensive, and artificial intelligence (AI) can offer improved efficiency gains. Could they be a match made in heaven? This Risk.net webinar, in association with NICE Actimize, took place amid the…
A new risk era – Recovering stronger from the pandemic
Jose Ribas, global head of risk and pricing solutions at Bloomberg, discusses how risk management at financial institutions is changing in the wake of the pandemic and the subsequent volatility, the role of regulations and how technology can help risk…
An alternative statistical framework for credit default prediction
This study compares the gradient-boosting model with four other well-known classifiers, namely, a classification and regression tree (CART), logistic regression (LR), multivariate adaptive regression splines (MARS) and a random forest (RF).
To model the real world, quants turn to synthetic data
Future financial models will be built using artificially generated data
Global macro views combine with quantitative models to produce consistent returns
The team behind River and Mercantile Group’s global macro strategy team operates under two key principles: that macro is the most important aspect of any investment decision and that decision-making should incorporate both systematic and discretionary…
How Goldman’s algos adapted to virus vol
Interview: Ralf Donner explains why algo usage is up while markets are down
Covid-19 tumult is testing AI fund returns
Some ML strategies have coped well, but others began to struggle as panic mounted
Deep learning calibration of option pricing models: some pitfalls and solutions
Addressing model calibration and the issue of no-arbitrage in a deep learning approach
Lighting up the black box: a must for investors?
Many contend you must be able to interpret machine learning in order to use it
At Numerai, real-world figures need not apply
AI hedge fund CEO sees the light in black-box technology
Factor strategies seesaw in coronavirus-hit markets
Quants struggle to second-guess ongoing effect of virus on investments
Top 10 op risks 2020: regulatory risk
New technology and reams of red tape make non-compliance fines more likely
Top 10 op risks 2020: talent risk
Firms struggle to reduce headcount and fill gaps without cutting corners
‘Quantamental’ approach convinces Morgan Creek CEO
Proponent of big-picture investing sees growing role for machines, but with caveats
Treasurers turn to AI in bid for sharper forecasting
Wider automation could usher in future of ‘hands-free hedging’, but obstacles lurk in data standards and sharing
Singapore banks tighten ML governance amid regulatory scrutiny
DBS, StanChart and Deutsche build model inventories and draw up standards around use cases
No silver bullet for AI explainability
No single approach to interpreting a neural network’s outputs is perfect, so it’s better to use them all