Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.31074

Directionally Correct Views in Portfolio Optimization

Ojas Kumar·Sreejit Dey·Sarvesh Ravichandran Iyer·Sandeep Juneja
View original source ↗Read source document ↗Export metadata ↓

Abstract

Portfolio optimization techniques often use historical data to estimate parameters for Markowitz-type or ML models. Effective allocation requires a way to align the available data with conditions expected over the investment horizon. Inspired by the Black-Litterman framework, we ask whether incorporating expert views leads to better portfolio allocations. In a simple Markowitz setting, we show that even a small amount of directionally correct information can materially improve investment decisions. We also discuss how expert views can be incorporated in end-to-end portfolio models using entropy-based ideas. Somewhat surprisingly, our empirical results indicate that simpler Markowitz-type model perform as well as an end-to-end model, once directionally correct experts are incorporated.

Explore related subjects

q-fin.PM

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Ojas Kumar, Sreejit Dey, Sarvesh Ravichandran Iyer, Sandeep Juneja. 2026-10-22. Directionally Correct Views in Portfolio Optimization. https://arxiv.org/abs/2610.31074

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Market Regime-Based Multi-Asset Portfolio Optimization Using Nested Clustered Optimization for Tactical Asset Allocation

We propose a regime-aware tactical asset allocation (TAA) framework integrating market regime detection with Nested Clustered Optimization (NCO) for multi-asset portfolio construction. The central hypothesis is that incorporating market regime information into the NCO pipeline, specifically at the stages of covariance estimation, hierarchical clustering, and weight optimization, yields portfolios with improved risk-adjusted performance and reduced downside risk relative to regime-agnostic baselines. Market regimes (Bullish, Sideways/Neutral, Bearish) are detected using a Gaussian Hidden Markov Model (HMM) fitted exclusively on information available up to each decision point, thereby preventing look-ahead bias. Regime-conditional covariance matrices and clustering structures parameterize NCO at each rebalancing event. An adaptive rebalancing rule, triggered by regime transitions or material changes in optimal weights, replaces fixed-calendar rebalancing. The framework is evaluated on a heterogeneous monthly multi-asset universe comprising Indonesian government bonds (SBN), the LQ45 equity index, gold (IDR-denominated), foreign exchange (CNY/IDR), and Bitcoin/IDR (BTC). Out-of-sample performance is assessed via rolling walk-forward backtesting. Benchmarks include equal-weight (1/N), buy-and-hold, standard NCO without regime awareness, minimum variance, hierarchical risk parity (HRP), and a rule-based regime strategy. Performance metrics include cumulative return, annualized Sharpe ratio, Sortino ratio, maximum drawdown, Calmar ratio, turnover, and net-of-cost returns. Statistical significance is assessed using the Jobson-Korkie test. The empirical analysis indicates that the proposed regime-aware TAA framework successfully limits tail risk, achieving a maximum drawdown of 4.44% and demonstrating the utility of HMM-based regime detection in multi-asset risk management.

q-fin.PM↗
arXiv2026

When Values-Based Screens Disagree: Continuous Shariah Compliance and Classification Dynamics

Does the design of a values-based screening rule generate eligibility changes when reported accounting inputs remain unchanged but market valuations move? We apply seven Shariah financial-screening rulebooks to 1.34 million U.S. security-months from 1999 to 2024 on a common, threshold-anchored scale. Applied retrospectively, the full emulations disagree on 35.9% of complete permissible-sector observations (38.8% from 2015, when all were in force), and the financial-ratio screens alone on 47.3%. Under AAOIFI's spot market-capitalisation denominator, market-capitalisation movement alone is sufficient for 65.6% of breaches, and half of denominator-driven breaches reverse within three months; numerator movement dominates under asset-based rules. Holding the threshold and sample fixed, a 24-month average denominator cuts debt-screen transitions from 2.51% to 1.03% a month, whereas raising the threshold barely matters. Among breaches of similar severity the reversal gap narrows but persists. Portfolio and fund-holdings evidence qualifies these findings: benefits are modest under a binding single-rule mandate.

q-fin.PM↗
arXiv2026

Regime-Aware Interpretable Ranking for Sector Rotation

Sector rotation is a common decision in benchmark-relative portfolio management, where portfolio managers rank sectors for overweight and underweight positions. We formulate this task as ranking sector actions by expected future risk-adjusted active performance, measured with forward sector-benchmark Sharpe ratios. Such rankings should preserve temporal information, express model outputs through economically familiar signal characteristics, account for changes in signal relevance across macroeconomic environments, and capture dependencies among sectors. We propose RegimeRank, an interpretable sector-ranking model that represents fundamental and technical signals through expert-defined temporal characteristics, conditions them on learned macro factors via cross-attention, and models cross-sector dependencies through self-attention. Expected-gradient attributions identify the contributions of individual signal-transformation pairs, while macroeconomic and cross-sector attention maps provide diagnostics of the learned conditioning and relational structure. We evaluate RegimeRank on weekly S&P 500 data from 2002 to 2024 under combinatorial purged cross-validation, where it outperforms representative ranking and machine-learning baselines across multiple ranking metrics. Ablation studies support the contributions of latent macro states, regime conditioning, and cross-sector modelling, while attribution and attention analyses illustrate the temporal characteristics, macro states, and sector relationships underlying its rankings.

q-fin.PM↗