Investments
Podcast: NYU’s Kolm on transaction costs and machine learning
TCA methodologies that ignore partial fills “might be off by 20% to 30%”
A principled approach to clean-up costs in algo trading
The opportunity cost associated with the cancelled portion of an order is quantified
Goal-based wealth management with reinforcement learning
A combination of machine learning techniques provides multi-period portfolio optimisation
Impact of hedging strategies on variable annuities
Put options may reduce the cost of hedging strategies for insurers
Zooming in on equity factor crowding
A measure for crowding in trades is derived from supply and demand imbalances
Time to move on from mean-variance diversification
A new diversification measure appears to produce better results than mean-variance optimisation
Equally diversified or equally weighted?
New diversification measure enables construction of equally diversified portfolios
Podcast: CFM’s Bouchaud on agent-based models and ESG investing
Hedge fund quant, and Risk.net’s new columnist, shares his unique take on markets
Spotting co-movement breakdowns with neural networks
Autoencoders can detect changes in relationship between assets in real time
Detecting changes in asset co-movement using autoencoders
ARR aims to anticipate volatility patterns to provide signals for risk management and trading
A closed-form solution for optimal mean-reverting strategies
The heat potentials method is used to find the optimal profit-taking and stop-loss levels
Stay ahead of the fixing lag
The price of fund-linked derivatives depends on the fixing lag of the underlying funds
A triptych approach for reverse stress testing of complex portfolios
Pascal Traccucci et al present an extended reverse stress test triptych approach with three variables
Forecasting value-at-risk
Alvin Stroyny and Tim Wilding build a dynamic risk framework for multi-asset global portfolios
Beyond Markowitz with quantum annealing
Venturelli and Kondratyev use quantum annealers to optimise portfolios
Tying allocation to selection
Hamza Bahaji introduces a new approach to core-satellite investing, the compound portfolio insurance
Black was right: price is within a factor 2 of value
CFM’s quants verify Fisher Black’s intuition on mean reversion still applies today
Emerging market corporate bonds as first-to-default baskets
Modified Merton model offers insights on EM corporate debt
Curve dynamics with artificial neural networks
Artificial neural networks can replace PCA for yield curves analysis
Machine learning for trading
Gordon Ritter applies reinforcement learning to dynamic trading strategies with market impact
Trading lightly: cross-impact and optimal portfolio execution
A liquidity model for basket of correlated securities is presented
Stress hedging in portfolio construction
Bilgili, Ferconi and Ulitsky propose a constrained portfolio optimisation approach incorporating stress scenarios
Fast and precautious: order controls for trade execution
Algo traders propose a new optimal execution algorithm with both limit and market orders
Optimal trading with linear and (small) non-linear costs
Bouchaud et al find the optimal trading strategy for a family of predictive signals in the presence of transaction costs