Forecasting
Canada’s top banks cut loan-loss provisions by $1.2bn
The decrease in set-asides represents a 92% fall quarter on quarter
Zone-wide prediction of generating unit-specific power outputs for electricity grid congestion forecasts
This paper explores various statistical and statistical learning methods, with the goal of adequately predicting the on/off status and power output levels of all power plants within a control zone.
Fake data can help backtesters, up to a point
Synthetic data made with machine learning will struggle to capture the caprice of financial markets
Modeling realized volatility with implied volatility for the EUR/GBP exchange rate
This paper concerns the application of implied volatility in modeling realized volatility in the daily, weekly and monthly horizon using high-frequency data for the EUR/GBP exchange rate.
The selection of predictive variables in aggregate hydroelectric generation models
This paper provides a method to identify the best predictive variables and the appropriate predictive indexes for an aggregate hydropower storage forecasting model. To this end, we use an entropy-based approach.
Neural network middle-term probabilistic forecasting of daily power consumption
The authors propose a new modeling approach that incorporates trend, seasonality and weather conditions as explicative variables in a shallow neural network with an autoregressive feature.
Forecasting Bitcoin returns: is there a role for the US–China trade war?
In this paper, the authors extend the related literature by examining whether the information on the US–China trade war can be used to forecast the future path of Bitcoin returns, controlling for various explanatory variables.
Buffer stops? Why banks haven’t used Covid capital relief
Amid weak credit demand, banks haven’t availed themselves of capital buffers, but they still might
The impact of data aggregation and risk attributes on stress testing models of mortgage default
In this paper, the authors investigate how data aggregation and risk attributes affect the development and performance of stress testing models by studying residential mortgage loan defaults.
US election scenarios: meltdown fears if poll contested
Crowdsourced election scenarios show sharp falls and correlation breaks if Trump challenges results
Back to school: BlackRock uses quant quake lessons on Covid
Pandemic prompts a switch in approach from strategic to tactical
Dutch banks seek quantum edge for stress tests
ABN, ING and Rabobank working together; US quantum developer seeks patent for CCAR
Power surge: the value of investing in renewables
Energy market expert investigates ways to forecast future power prices and capture rates in order to value renewables PPAs
Podcast: Dario Villani on managing money with ML
Duality’s CEO discusses key to machine learning success, and the influence of Renaissance’s Jim Simons
Study suggests banks may be better off with simpler VAR models
Non-parametric VAR models perform well in calm markets, but miss the mark in volatile periods
IFRS 9 and the loan loss lottery
As reserves for bad loans balloon, banks grapple with measuring Covid-era credit risk
Sometimes it’s fine to be boring
Diversification puts portfolios in the middle of the pack – where investors feel safe, writes Antonia Lim
Volatility spillover along the supply chains: a network analysis on economic links
The analysis in this paper reveals that additional fundamental risk gets transferred along supply chains, and that suppliers are exposed to additional fundamental risk that is not captured by their market beta. Suppliers are therefore exposed to…
Range-based volatility forecasting: a multiplicative component conditional autoregressive range model
This paper proposes a multiplicative component CARR (MCCARR) model to capture the "long-memory" effect in volatility.
Old-fashioned parametric models are still the best: a comparison of value-at-risk approaches in several volatility states
The authors present backtesting results for 1% and 2.5% VaR of six indexes from emerging and developed countries using several of the best-known VaR models, including generalized autoregressive conditional heteroscedasticity (GARCH), extreme value theory…
Doyne Farmer’s next big adventure: capturing the universe
Quant fund pioneer plans to build an economic super-simulator on a global scale
In downturns, vol travels down the supply chain – study
Customer VAR breaches strike at stressed suppliers, research shows
R-nought is the wrong number for markets, academics say
New research suggests volatility of transmission matters more for asset prices