Topic
Portfolio & Allocation
Portfolio construction, allocation, rebalancing and risk budgeting, from Markowitz to deep RL.
- Papers featured
- 659
- Last 12 months
- 72
- Cited 100+
- 0
- Top venue
- SSRN
Featured per quarter
The last four quarters are highlighted.
Methods that come up
Click one to search for it.
Most cited
Featured papers in this topic with the most citations today.
- 29 Nov 202335cites
Missing values handling for machine learning portfolios
The study shows that using cross-sectional means for simple imputation is effective in dealing with missing values in machine learning-constructed portfolios, as complex imputations can cause underperformance due to estimation noise.
arXivIn Journal of Financial EconomicsFeatured 2×
- 12 Oct 202327cites
Technical Note - An Unexpected Stochastic Dominance: Pareto Distributions, Dependence, and Diversification
The research suggests that diversifying super-Pareto losses increases portfolio risk, discouraging risk sharing in market equilibrium.
arXivIn Oper. Res.
- 3 Oct 202525cites
AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration
Alpha Mining: AlphaSAGE, a new framework for automated alpha mining in quantitative finance, uses a structure-aware encoder and Generative Flow Networks to overcome challenges and outperforms existing methods in creating a diverse and predictive portfolio of alphas.
arXiv
- 20 Jun 202425cites
Dynamic asset allocation with asset-specific regime forecasts
The article introduces a new framework that enhances multi-asset portfolio construction by creating custom regime forecasts for each asset, proven effective through a practical study on a multi-asset portfolio.
arXivIn Annals of Operations Research
- 23 Jan 202424cites
MAD risk parity portfolios
Features & Performance: A study using the Mean Absolute Deviation (MAD) to measure risk in the Risk Parity (RP) model found that RP strategies typically perform between minimum risk and equally weighted strategies.
arXivIn Annals of Operations Research
- 7 Feb 202420cites
Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management
The piece introduces a multi-agent and self-adaptive framework (MASA) for portfolio management, using reinforcement learning to balance returns and risks, providing market trend feedback and outperforming other similar approaches.
arXivIn Adaptive Agents and Multi-Agent SystemsFeatured 2×
- 24 Jul 202419cites
Explainable post hoc portfolio management financial policy of a Deep Reinforcement Learning agent
A new Explainable Deep Reinforcement Learning (XDRL) method for portfolio management has been developed, combining Proximal Policy Optimization with explainable techniques for better transparency in investment predictions.
arXivIn PLOS ONEFeatured 2×
- 24 May 202318cites
Risk Budgeting Allocation for Dynamic Risk Measures
Risk budgeting allocation approach developed using dynamic risk contributions and deep learning.
arXivIn Oper. Res.
- 29 Nov 202317cites
On Optimal Tracking Portfolio in Incomplete Markets: The Reinforcement Learning Approach
The paper uses capital injection to solve an optimal tracking portfolio problem in incomplete market models, showcasing the q-learning algorithm's performance.
arXivIn SIAM J. Control. Optim.
- 20 Dec 202316cites
Data-Driven Merton's Strategies via Policy Randomization
The study applies reinforcement learning to determine optimal portfolio policies in an incomplete market, showing its efficiency and robustness compared to the traditional plug-in method.
arXivFeatured 3×
- 14 May 202515cites
Loss-Versus-Rebalancing under Deterministic and Generalized block-times
A study reveals that constant block intervals in blockchain settings provide the best protection against arbitrage for Automated Market Makers' liquidity providers, using random walk theory.
arXiv
- 5 Sep 202415cites
Sparse spanning portfolios and under-diversification with second-order stochastic dominance
A new method for estimating sparse second-order stochastic spanning suggests no advantage in expanding a sparse opportunity set beyond 45 assets, with the best sparse portfolio investing in 10 sectors.
arXiv
Latest
- 6 Nov 20263fanfare
Penalize the Common Trade: A Collision-Aware Layer for Learned Portfolios
A post-model layer that reduces portfolio concentration by penalizing shared exposures cuts maximum drawdown from 23.6% to 14.1% on a cross-asset test.
arXiv
- 6 Nov 20264fanfare
The Hidden Sharpe Ratio
The study estimates maximum Sharpe ratios in large cross-sections without constructing the efficient portfolio, finding annualized maximal Sharpe of 7.4 in U.S. equities versus benchmark estimates of 1.0 to 4.0.
SSRN
- 6 Nov 20263fanfare
Risk-Budgeted Mean-Variance Portfolios
A convex optimization method combines risk budgeting with expected returns, delivering higher average returns than risk parity with lower turnover and concentration than traditional mean-variance portfolios.
SSRN
- 6 Nov 20263fanfare
When Cash Flows Turn Negative: Liquidity-Driven Selling by Pension Funds
U.S. pension funds facing negative cash flows sell equities as primary liquidity source rather than rebalancing, absorbing $0.67 per dollar of shock through equity sales.
RePEc
- 6 Nov 20262fanfare
Performance Persistence in Private Equity: Skill, Structure, and Statistical Artefacts
Literature review finds genuine skill in private equity performance persistence, especially in venture capital, but shows estimates often weaken under stricter methods and richer data.
RePEc
- 30 Oct 20262fanfare
Sparse Autoencoders as Implicit Diversification Regularisers for Cross-Sectional Cryptocurrency Returns
Sparse autoencoders extract interpretable factors from cryptocurrency returns and produce lower-volatility portfolios through better asset diversification, though without outperforming simple contrarian strategies.
arXiv
- 30 Oct 20262fanfare
Measuring Longer-Horizon Leveraged ETF Performance
The study shows that measuring leveraged ETF performance with arithmetic mean compounding can rank investments backwards and proposes using realized terminal wealth and expected log returns instead.
arXiv
- 30 Oct 20262fanfare
Distributionally robust chance-constrained standard quadratic optimization with Wasserstein ambiguity
A tractable mixed-integer reformulation solves distributionally robust portfolio optimization over a Wasserstein ball, unifying chance-constrained and value-at-risk formulations.
arXiv
- 30 Oct 20262fanfare
Continuous-Time Mean-Variance Portfolio Selection Reinforcement Learning Problems for a Markov Regime-Switching System with No-Shorting Constraints
The study develops a model-free reinforcement learning algorithm that learns optimal no-shorting portfolio policies from trajectory data in regime-switching markets by decoupling constraints from policy exploration.
arXiv
- 30 Oct 20262fanfare
Replicating USMV and SPLV with a Public-data Factor Risk ModelSpecification Ambiguity Dominates the Choice of Covariance Estimator
Rebuilding low-volatility indices from public data shows that a rank-based method replicates closely but an optimization-based method fails due to index-specification ambiguity, not covariance estimation.
SSRN
- 30 Oct 20262fanfare
Investment Mandates and the Value of Distribution Timing in Currency Portfolios Choice
Adding skewness and kurtosis to mean-variance allocations in currency markets produces economically meaningful gains that depend critically on the investment mandate and ability to adjust gross exposure.
SSRN
- 30 Oct 20262fanfare
Multi-factor Investing in Borsa Istanbul
A five-characteristic long-only strategy for Turkish stocks earns 4.4% annual alpha against the cap-weighted index, but equal-weighted scaling erodes the advantage, suggesting gains come from breadth and risk management rather than characteristics.
SSRN
- 30 Oct 20263fanfare
Does shareholder diversification enhance firm investment resilience? Evidence from the euro area
Firms with home-biased shareholders cut investment 20% more than diversified peers during the pandemic, revealing equity concentration weakens corporate resilience to shocks.
RePEc
- 30 Oct 20262fanfare
Firm Heterogeneity and the Response of Investment to Monetary Policy
The research documents that most firms respond little to interest rate changes, but some show strong sensitivity; substantial heterogeneity cannot be easily explained by standard firm traits.
RePEc
- 23 Oct 20260cites
Dynamic Programming for Value-at-Risk Markov Decision Processes in Continuous Spaces
The paper establishes validity of dynamic programming equations for Value-at-Risk objectives in continuous state and action spaces, enabling optimal execution problems with VaR goals.
arXiv
- 23 Oct 20260cites
Optimal Trading Filters and the Value of Predictive Signals
Wiener-Hopf factorization yields optimal trading filters for return forecasts under transient price impact, showing fractional filters and the value of mean-reversion timing for signals.
arXiv
- 23 Oct 20260cites
Market Regime-Based Multi-Asset Portfolio Optimization Using Nested Clustered Optimization for Tactical Asset Allocation
The study integrates market regime detection with Nested Clustered Optimization to build multi-asset portfolios, showing improved risk-adjusted returns and reduced downside risk versus regime-agnostic approaches.
arXiv
- 23 Oct 20260cites
Deep catastrophic-risk-aware reinforcement learning
The study applies extreme value theory to train neural hedging policies on tail risk, achieving lower losses under extreme scenarios when relevant observations are scarce.
arXiv
- 23 Oct 20260cites
Directionally Correct Views in Portfolio Optimization
The research shows that even small amounts of directionally correct expert information materially improve portfolio allocations in both classical and machine-learning frameworks.
arXiv
- 23 Oct 20263fanfare
A Model of Price Impact and Fire Sales in Crowded Trades
A model of factor crowding shows that forced exits amplify shocks up to sixfold and shift crowding costs from average returns into tail losses.
SSRN
- 23 Oct 20262fanfare
Factor Timing with Transaction Costs
A strategy dynamically allocating across 50 smart-beta factors based on past returns and covariances significantly outperforms static allocation even with transaction costs included.
SSRN
- 23 Oct 20262fanfare
Crowded Factors and Volatility Timing: When Risk Scaling Works
Crowding combined with volatility and market stress improves the risk-adjusted performance of volatility-managed factors more than standard volatility management alone.
SSRN
- 23 Oct 20263fanfare
Returns to Private Debt in Emerging and Developing Economies
Analysis of 4,109 loans totaling $115 billion reveals that post-crisis private debt in emerging economies outperforms both emerging-market bonds and Treasuries with public market equivalents above 1.02.
RePEc
- 23 Oct 20263fanfare
Financing the AI Buildout
Estimates show a 188 GW U.S. AI campus buildout requires nearly $9 trillion through 2032, shifting toward leases, joint ventures, and structures that raise leverage and opacity.
RePEc
- 23 Oct 20262fanfare
Communicating Performance: Textual and Financial Disclosures in Private Equity
The study finds that early textual discussions of portfolio companies better predict ultimate performance, while interim valuations matter more later, signaling general partner quality.
RePEc
- 16 Oct 20260cites
From Economic Explanation to Performance Improvement in Machine-Learning Portfolios
A first-order attribution framework maps feature exposures to portfolio-performance sensitivities, enabling post-training intervention that improves net Sharpe ratios without retraining.
arXiv
- 16 Oct 20260cites
Data-Driven Dynamic Portfolio Selection with Vine Copula Simulation and Reinforcement Learning
A data-driven approach combines vine-copula simulation with reinforcement learning to optimize dynamic portfolio selection across equities and gold with CVaR penalties.
arXiv
- 16 Oct 20263fanfare
Multi-Asset Portfolio Selection with Machine Learning: Long-Run International Evidence
Machine learning forecasts of equity, bond, bill and housing returns from 1870-2020 across 16 countries improve Sharpe ratios substantially when trained on pooled cross-country data rather than country-specific samples.
SSRN
- 16 Oct 20262fanfare
From Regimes to Portfolios: An Interpretable Machine-Learning Framework for Strategic and Tactical Cross-Asset Allocation
An interpretable machine-learning framework linking regime identification to cross-asset portfolio construction earns 0.60 net Sharpe, not significantly different from a 60/40 benchmark.
SSRN
- 16 Oct 20262fanfare
Malliavin-Informed Policy Gradients for Continuous-Time Portfolio Optimization Neural Variance Reduction under Black-Scholes, Heston, and Rough Bergomi Dynamics
The paper develops a Malliavin-informed policy-gradient estimator using stochastic control variates to reduce variance in continuous-time reinforcement learning for dynamic portfolio selection.
SSRN