Machine Learning Classification and Portfolio Construction: Does the Loss Function Matter?

Yang Bai; Kuntara Pukthuanthong

q-fin.GNAug 4, 2021

Machine Learning Classification and Portfolio Construction: Does the Loss Function Matter?

Authors: Yang Bai, Kuntara Pukthuanthong

Organizations: College of Business and Economics, California State University, Fullerton · Trulaske Sr. College of Business, University of Missouri

Abstract

Classification outperforms regression across matched machine learning models in portfolio construction. A stacking ensemble of gradient boosted tree, random forest, and neural network yields a value-weighted annualized Sharpe ratio of 1.83 for classification and 1.11 for regression. This outperformance persists in multiclass settings, across subsamples, and after transaction costs. Spanning tests show that classification retains economically large alphas after we control for regression, whereas regression alphas shrink substantially once we control for classification. These results indicate that classification extracts more return information than matched regression. Our diagnostics trace classification's advantage to sharper and more precise separation of return deciles.

Explore similar work

From Financial Sentiment Classification to Return Predictability: A QLoRA Benchmark of Large Language Models
Aug 4, 2026Fusheng LuoFinancial Sentiment Analysis Legal Natural Language Processing Benchmarks
MAPLE: Efficient and Diverse Multi-Alpha Generation for Portfolio Construction
Jul 27, 2026Yu-Chen Den, Kuan-Yu Chen, Kendro Vincent +1Portfolio Optimization Market
Ratio-based Loss Functions
May 7, 2026Lena Helgerth, Andreas ChristmannLoss Function Lipschitz Constant

Aug 4, 2026 · q-fin.MFJ/K move · Enter open · S save

From Financial Sentiment Classification to Return Predictability: A QLoRA Benchmark of Large Language Models

Fusheng Luo

Johns Hopkins University Baltimore, Maryland, USA

Financial sentiment classifiers are commonly evaluated against human labels, but strong linguistic performance does not necessarily imply economically useful return predictability. This study separates these questions through two experiments. First, we construct a unified three-class benchmark from five financial text datasets and compare TF--IDF Naive Bayes, off-the-shelf FinBERT and Financial-RoBERTa encoders, zero-shot Qwen2.5-7B, and QLoRA-adapted Qwen2.5-7B, LLaMA3-8B, and Mistral-7B models. Mistral-7B achieves the best test accuracy (0.8840) and macro-F1 (0.8771), while QLoRA raises Qwen2.5's macro-F1 from 0.7274 to 0.8615. An inverse-frequency class-weighted loss does not improve Qwen2.5. Second, we evaluate economic validity on a temporally separate 2019 Benzinga sample containing 10,637 unique headlines and 13,115 headline--stock observations for a fixed S&P~100 universe. Model probabilities are converted into continuous sentiment scores, aggregated by stock and signal date, and aligned with next-session returns over one-, two-, three-, and five-day horizons. All seven downstream models produce positive but small mean rank information coefficients at the one-day horizon; the largest is 0.0143 for FinBERT. None of the 28 model--horizon tests remains significant after Newey--West inference and false-discovery-rate correction. Portfolio results likewise fail to establish a robust advantage for the best-performing classifiers. The findings show that QLoRA is effective for financial sentiment adaptation, while also documenting a clear gap between classification accuracy and tradable cross-sectional signals.

Financial Sentiment Analysis Legal Natural Language Processing Benchmarks Low-Rank Adaptation

Open paper Ask about it PDF

Abstract

Explore similar work

From Financial Sentiment Classification to Return Predictability: A QLoRA Benchmark of Large Language Models

MAPLE: Efficient and Diverse Multi-Alpha Generation for Portfolio Construction

Ratio-based Loss Functions