Regret-Based Portfolio Allocation: Minimizing Opportunity Cost and Its Dispersion

<p><span>Investors increasingly judge portfolios by how much they lag ex‑post winners rather than by absolute Sharpe ratios, turning missed opportunities into a first‑order driver of dissatisfaction. This paper addresses the resulting gap between regret‑based evaluation and traditional risk models that manage the dispersion of portfolio returns instead of the dispersion of regret. We develop a Mean–MAD Regret framework that treats regret—not returns—as the primary object of risk management. The model defines period‑by‑period regret as the shortfall between </span><span>a dynamic benchmark and portfolio returns</span><span>, and then minimizes a Mean Absolute Deviation objective on this regret series using a single parameter to govern the trade‑off between average regret and regret dispersion.</span></p> <p><span>In a diversified multi‑asset universe of equities, fixed income, commodities and real assets, regret‑based portfolios with low to moderate dispersion aversion </span><span>deliver higher compound returns and competitive or superior risk-adjusted performance relative to standard diversification heuristics and risk-based strategies, at the cost of greater concentration and drawdown risk</span><span>. The main contribution is to provide an operational way to manage the level and volatility of opportunity cost relative to a dynamic benchmark, offering institutional investors a transparent tool to align portfolio construction with how performance is actually assessed.</span></p>