The DOI matches its Crossref record; 94 of the 94 references it cites were found in a registry or an index; 6 of the 42 sources its claims cite were checked for support.
Empirical asset pricing via machine learning: evidence from the European stock market
Open accessAbstract
This paper evaluates the predictive performance of machine learning methods in forecasting European stock returns. Compared to a linear benchmark model, interactions and nonlinear effects help improve the predictive performance. But machine learning models must be adequately trained and tuned to overcome the high dimensionality problem and to avoid overfitting. Across all machine learning methods, the most important predictors are based on price trends and fundamental signals from valuation ratios. However, the models exhibit substantial variation in statistical predictive performance that translate into pronounced differences in economic profitability. The return and risk measures of long-only trading strategies indicate that machine learning models produce sizeable gains relative to our benchmark. Neural networks perform best, also after accounting for transaction costs. A classification-based portfolio formation, utilizing a support vector machine that avoids estimating stock-level expected returns, performs even better than the neural network architecture.
Overview
CoChat Summary
TL;DR
This paper evaluates machine learning methods for forecasting European stock returns against a linear Fama–MacBeth benchmark using 22 firm-level predictors, and finds that interactions and nonlinear effects improve predictive performance when models are adequately trained and tuned. Neural networks perform best among expected-return-based approaches, but a classification-based support vector machine that avoids estimating stock-level expected returns performs even better.
Key findings
- Machine learning models beat the linear benchmark on out-of-sample predictive R² (full sample): ols_full −0.52%, ols_pars 0.57%, elanet 1.21%, pcr 1.24%, pls 1.08%, rf 1.18%, gbrt 1.14%, nn_1 1.23%. Predictive slopes were closest to 1 for rf (1.03), gbrt (1.07), and nn_1 (0.98), versus 0.65 for ols_pars and 0.45 for ols_full.
- The most important predictors across models are based on recent price trends (e.g., short-term reversal, momentum) and fundamental valuation signals (e.g., earnings-to-price, book-to-market); tree-based models concentrate weight on few variables, while dimension-reducing models spread importance more widely.
- Long-only equal-weighted portfolios: nn_1 produced a monthly H–L spread of 3.26% (return ratio 1.04, annualized Sharpe 3.89, t-stat 13.96); the ols_pars portfolio reached a terminal value of €70.29 versus €107.18 for nn_1 before transaction costs, and €17.02 versus €26.01 after applying a conservative 57 bps monthly cost.
- The SVM classification approach slightly outperformed nn_1: accuracy 12.63% vs. 12.10% (random classifier 10.04%), and higher terminal values (€113.57 vs. €107.18 equal-weighted before costs; €27.57 vs. €26.01 after costs).
Methods
- Sample: all firms publicly listed in one of the nineteen Eurozone countries as of December 2020, monthly data from Thomson Reuters Datastream, January 1990–December 2020; average universe of 832 firms (range 56 to 1,012); average monthly excess return 0.51% (SD 4.55%); minimum €25 mill. market cap and at least 50 qualifying firms per month.
- Predictors: 22 firm-level characteristics from Drobetz et al. (2019), plus 44 country/SIC dummies (parsimonious set = 66 covariates) and, in the full set, two-way interactions and second/third-order polynomials (341 covariates); characteristics winsorized at 1%/99% and rank-mapped to (−1, +1).
- Models: OLS (parsimonious and full), elastic net, PCR, PLS, random forests, gradient boosted regression trees, feedforward neural networks (nn_1–nn_5), and a support vector machine for classification-based portfolio formation; rolling-window time-series cross-validation with 8 years training, 2 years validation, 1 year testing, annual re-estimation; evaluation via predictive slopes, predictive R², modified Diebold–Mariano tests, decile portfolio sorts, conditional CAPM/FF5M alphas, and long-only portfolio performance net of transaction costs.
Limitations
- The paper states that neural networks are computationally intensive and can be specified in innumerable architectures, so the authors pre-specify five models and treat nn_1–nn_5 as "a conservative lower bound" for neural network performance; they also note that deeper networks deteriorated quickly, possibly due to overfitting on a relatively small dataset.
- The paper notes that the DM test's weak error dependence assumption may be questionable due to potentially strong cross-sectional return dependence, and that pre-estimation variable selection based on full-sample importance metrics could introduce foresight bias.
- Evident from the text: the applied 57 bps monthly transaction cost is described as an overly conservative discount that pushes most value-weighted portfolios below the benchmark, and the authors caution that statistical and economic performance may be only weakly associated (citing Leitch and Tanner 1991).
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures










Verification
Claims the paper makes
5 Valid · 6 Not valid · 27 Not checked · 194 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Although the transaction cost models of Bollerslev et al. (2018) and Koijen et al. (2018) are quite conservative, we follow an even more cautious approach and deduct 57 bps from each portfolio's monthly excess returns.”
§ Avg Std Definition Excess return [%] 0.51 4.55 Return in excess of the 3-month EURIBOR rate (scaled to the 1-month horizon) 1 size 13.22 0.48 Log market value of equity at the end of the prior month 2 bm -0.55 0.18 Log book value of equity minus log market value of equity at the end of the prior month 3 operatingprofitability 0.06 0.01 Operating profit divided by average total assets in the prior fiscal year 4 totalassetgrowth 0.07 0.04 Log total asset growth in the prior fiscal year 5 ret_2_12 0.09 0.20 Excess return from month -12 to month -2 6 issues_1_36 0.09 0.02 Log growth in split-adjusted shares outstanding from month -36 to month -1 7 accrualschange -0.04 0.01 Working capital accruals (based on Sloan 1996) in the prior fiscal year 8 roa 0.05 0.01 Income before extraordinary items divided by average total assets (return on assets) in the prior fiscal year 9 investment 1.02 0.08 Capital expenditures divided by net sales and revenues in the prior fiscal year 10 ret_1 0.01 0.05 Excess return of the prior month 11 ret_12_36 0.09 0.31 Excess return from month -36 to month -12 12 dy 0.03 0.01 Dividends per share over the prior 12 months divided by price at the end of the prior month 13 beta 0.83 0.10 Market beta, estimated from weekly returns from month -36 to month -1 14 vola 0.32 0.06 Standard deviation, estimated from weekly returns from month -12 to month -1 15 turnover 0.02 0.01 Average monthly turnover volume from month -12 to month -1 16 debttoprice 0.84 0.32 Short-term plus long-term debt in the prior fiscal year divided by market capitalization at the end of the prior month 17 salestoprice 2.16 0.60 Net sales and revenues in the prior fiscal year divided by market capitalization at the end of the prior month 18 cftoprice 0.14 0.04 Net income plus depreciation, depletion and amortization in the prior fiscal year divided by market capitalization at the end of the prior month 19 earningstoprice 0.04 0.02 Net income in the prior fiscal year divided by market capitalization at the end of the prior month 20 issues_1_12 0.02 0.01 Log growth in split-adjusted shares outstanding from month -12 to month -1 21 fcdispersion -2.05 0.18 Log standard deviation of I/B/E/S EPS forecasts minus log average absolute value of I/B/E/S EPS forecasts from month -12 to month -1 22 grossprofitability 0.30 0.03 Net sales and revenues minus costs of goods sold divided by average total assets in the prior fiscal year Sample size 832 Number of firms with non-missing observations for the excess return and each of the twenty-two characteristics > Investment portfolio performance
What the sources say
- Supportedcites Bollerslev et al. (2018) source
Section 5.3 (p. 35) says Bollerslev et al. use the full bid-ask spread rather than the customary half-spread for their benchmark transaction-cost estimate, allowing for potentially higher costs from market impact. That supports describing their cost assumption as conservative; this verdict addresses only Bollerslev et al., not the separately cited Koijen et al. paper. (LLM, conf=0.86)
- Partly supportedcites Koijen et al. (2018) sourceExperimental — accuracy not yet measured
Section 4.2 calls Koijen et al.'s transaction-cost estimate conservative for options because the quoted spreads likely overstate realistic costs. The Introduction describes its estimates for other asset classes as realistic, so the blanket characterization of its transaction-cost model as conservative is broader than the paper supports. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This is our benchmark model, and it is able to explain a substantial percentage of the cross-sectional variation in European stock returns.”
§ Empirical asset pricing via machine learning: evidence from the European stock market > Introduction
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Although they use the FM regressions model that is re-estimated on a monthly basis, the ols_pars model provides nearly identical predictions in our sample-splitting and reestimation setting.”
§ Avg Std Definition Excess return [%] 0.51 4.55 Return in excess of the 3-month EURIBOR rate (scaled to the 1-month horizon) 1 size 13.22 0.48 Log market value of equity at the end of the prior month 2 bm -0.55 0.18 Log book value of equity minus log market value of equity at the end of the prior month 3 operatingprofitability 0.06 0.01 Operating profit divided by average total assets in the prior fiscal year 4 totalassetgrowth 0.07 0.04 Log total asset growth in the prior fiscal year 5 ret_2_12 0.09 0.20 Excess return from month -12 to month -2 6 issues_1_36 0.09 0.02 Log growth in split-adjusted shares outstanding from month -36 to month -1 7 accrualschange -0.04 0.01 Working capital accruals (based on Sloan 1996) in the prior fiscal year 8 roa 0.05 0.01 Income before extraordinary items divided by average total assets (return on assets) in the prior fiscal year 9 investment 1.02 0.08 Capital expenditures divided by net sales and revenues in the prior fiscal year 10 ret_1 0.01 0.05 Excess return of the prior month 11 ret_12_36 0.09 0.31 Excess return from month -36 to month -12 12 dy 0.03 0.01 Dividends per share over the prior 12 months divided by price at the end of the prior month 13 beta 0.83 0.10 Market beta, estimated from weekly returns from month -36 to month -1 14 vola 0.32 0.06 Standard deviation, estimated from weekly returns from month -12 to month -1 15 turnover 0.02 0.01 Average monthly turnover volume from month -12 to month -1 16 debttoprice 0.84 0.32 Short-term plus long-term debt in the prior fiscal year divided by market capitalization at the end of the prior month 17 salestoprice 2.16 0.60 Net sales and revenues in the prior fiscal year divided by market capitalization at the end of the prior month 18 cftoprice 0.14 0.04 Net income plus depreciation, depletion and amortization in the prior fiscal year divided by market capitalization at the end of the prior month 19 earningstoprice 0.04 0.02 Net income in the prior fiscal year divided by market capitalization at the end of the prior month 20 issues_1_12 0.02 0.01 Log growth in split-adjusted shares outstanding from month -12 to month -1 21 fcdispersion -2.05 0.18 Log standard deviation of I/B/E/S EPS forecasts minus log average absolute value of I/B/E/S EPS forecasts from month -12 to month -1 22 grossprofitability 0.30 0.03 Net sales and revenues minus costs of goods sold divided by average total assets in the prior fiscal year Sample size 832 Number of firms with non-missing observations for the excess return and each of the twenty-two characteristics > Ordinary least squares
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Across all machine learning methods, the most important predictors are based on price trends and fundamental signals from valuation ratios.”
- Also stated in: § Introduction · plain
“The most influential predictors are based on recent price trends, e.g., short-term reversal and stock momentum, and fundamental signals from valuation ratios, e.g., earnings-to-price and book-to-market ratios.”
§ Empirical asset pricing via machine learning: evidence from the European stock market > Abstract
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Introduction · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the models exhibit substantial variation in statistical predictive performance that translate into pronounced differences in economic profitability.”
- Also stated in: § Introduction · plain
“Despite these commonalities, our forecast models exhibit differences in statistical predictive performance (as indicated by predictive slopes, predictive R 2 metrics, and Die- bold and Mariano (1995) test statistics), which also translate into marked differences in economic profitability.”
§ Empirical asset pricing via machine learning: evidence from the European stock market > Abstract
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Introduction · plain
99 more claims
Create a free account to see all 232 claims and every source verdict.
- It may state two separate claims as one. 63
- Probably not a substantial claim. 62
- The quote only partly states this claim. 26
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Avg Std Definition Excess return [%] 0.51 4.55 Return in excess of the 3-month EURIBOR rate (scaled to the 1-month horizon) 1 size 13.22 0.48 Log market value of equity at the end of the prior month 2 bm -0.55 0.18 Log book value of equity minus log market value of equity at the end of the prior month 3 operatingprofitability 0.06 0.01 Operating profit divided by average total assets in the prior fiscal year 4 totalassetgrowth 0.07 0.04 Log total asset growth in the prior fiscal year 5 ret_2_12 0.09 0.20 Excess return from month -12 to month -2 6 issues_1_36 0.09 0.02 Log growth in split-adjusted shares outstanding from month -36 to month -1 7 accrualschange -0.04 0.01 Working capital accruals (based on Sloan 1996) in the prior fiscal year 8 roa 0.05 0.01 Income before extraordinary items divided by average total assets (return on assets) in the prior fiscal year 9 investment 1.02 0.08 Capital expenditures divided by net sales and revenues in the prior fiscal year 10 ret_1 0.01 0.05 Excess return of the prior month 11 ret_12_36 0.09 0.31 Excess return from month -36 to month -12 12 dy 0.03 0.01 Dividends per share over the prior 12 months divided by price at the end of the prior month 13 beta 0.83 0.10 Market beta, estimated from weekly returns from month -36 to month -1 14 vola 0.32 0.06 Standard deviation, estimated from weekly returns from month -12 to month -1 15 turnover 0.02 0.01 Average monthly turnover volume from month -12 to month -1 16 debttoprice 0.84 0.32 Short-term plus long-term debt in the prior fiscal year divided by market capitalization at the end of the prior month 17 salestoprice 2.16 0.60 Net sales and revenues in the prior fiscal year divided by market capitalization at the end of the prior month 18 cftoprice 0.14 0.04 Net income plus depreciation, depletion and amortization in the prior fiscal year divided by market capitalization at the end of the prior month 19 earningstoprice 0.04 0.02 Net income in the prior fiscal year divided by market capitalization at the end of the prior month 20 issues_1_12 0.02 0.01 Log growth in split-adjusted shares outstanding from month -12 to month -1 21 fcdispersion -2.05 0.18 Log standard deviation of I/B/E/S EPS forecasts minus log average absolute value of I/B/E/S EPS forecasts from month -12 to month -1 22 grossprofitability 0.30 0.03 Net sales and revenues minus costs of goods sold divided by average total assets in the prior fiscal year Sample size 832 Number of firms with non-missing observations for the excess return and each of the twenty-two characteristics > Machine learning method: Support vector machines
“Smaller misclassification costs c allow us to ignore more of the misclassified support vectors, while continuing to fit optimal hyperplanes.”
§ Avg Std Definition Excess return [%] 0.51 4.55 Return in excess of the 3-month EURIBOR rate (scaled to the 1-month horizon) 1 size 13.22 0.48 Log market value of equity at the end of the prior month 2 bm -0.55 0.18 Log book value of equity minus log market value of equity at the end of the prior month 3 operatingprofitability 0.06 0.01 Operating profit divided by average total assets in the prior fiscal year 4 totalassetgrowth 0.07 0.04 Log total asset growth in the prior fiscal year 5 ret_2_12 0.09 0.20 Excess return from month -12 to month -2 6 issues_1_36 0.09 0.02 Log growth in split-adjusted shares outstanding from month -36 to month -1 7 accrualschange -0.04 0.01 Working capital accruals (based on Sloan 1996) in the prior fiscal year 8 roa 0.05 0.01 Income before extraordinary items divided by average total assets (return on assets) in the prior fiscal year 9 investment 1.02 0.08 Capital expenditures divided by net sales and revenues in the prior fiscal year 10 ret_1 0.01 0.05 Excess return of the prior month 11 ret_12_36 0.09 0.31 Excess return from month -36 to month -12 12 dy 0.03 0.01 Dividends per share over the prior 12 months divided by price at the end of the prior month 13 beta 0.83 0.10 Market beta, estimated from weekly returns from month -36 to month -1 14 vola 0.32 0.06 Standard deviation, estimated from weekly returns from month -12 to month -1 15 turnover 0.02 0.01 Average monthly turnover volume from month -12 to month -1 16 debttoprice 0.84 0.32 Short-term plus long-term debt in the prior fiscal year divided by market capitalization at the end of the prior month 17 salestoprice 2.16 0.60 Net sales and revenues in the prior fiscal year divided by market capitalization at the end of the prior month 18 cftoprice 0.14 0.04 Net income plus depreciation, depletion and amortization in the prior fiscal year divided by market capitalization at the end of the prior month 19 earningstoprice 0.04 0.02 Net income in the prior fiscal year divided by market capitalization at the end of the prior month 20 issues_1_12 0.02 0.01 Log growth in split-adjusted shares outstanding from month -12 to month -1 21 fcdispersion -2.05 0.18 Log standard deviation of I/B/E/S EPS forecasts minus log average absolute value of I/B/E/S EPS forecasts from month -12 to month -1 22 grossprofitability 0.30 0.03 Net sales and revenues minus costs of goods sold divided by average total assets in the prior fiscal year Sample size 832 Number of firms with non-missing observations for the excess return and each of the twenty-two characteristics > Appendix 1
“svm c {0.01, 0.05, 0.1, 0.5, 1} Vector influence γ {0.01, 0.05, 0.1, 0.5, 1} Misclassification costs”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Avg Std Definition Excess return [%] 0.51 4.55 Return in excess of the 3-month EURIBOR rate (scaled to the 1-month horizon) 1 size 13.22 0.48 Log market value of equity at the end of the prior month 2 bm -0.55 0.18 Log book value of equity minus log market value of equity at the end of the prior month 3 operatingprofitability 0.06 0.01 Operating profit divided by average total assets in the prior fiscal year 4 totalassetgrowth 0.07 0.04 Log total asset growth in the prior fiscal year 5 ret_2_12 0.09 0.20 Excess return from month -12 to month -2 6 issues_1_36 0.09 0.02 Log growth in split-adjusted shares outstanding from month -36 to month -1 7 accrualschange -0.04 0.01 Working capital accruals (based on Sloan 1996) in the prior fiscal year 8 roa 0.05 0.01 Income before extraordinary items divided by average total assets (return on assets) in the prior fiscal year 9 investment 1.02 0.08 Capital expenditures divided by net sales and revenues in the prior fiscal year 10 ret_1 0.01 0.05 Excess return of the prior month 11 ret_12_36 0.09 0.31 Excess return from month -36 to month -12 12 dy 0.03 0.01 Dividends per share over the prior 12 months divided by price at the end of the prior month 13 beta 0.83 0.10 Market beta, estimated from weekly returns from month -36 to month -1 14 vola 0.32 0.06 Standard deviation, estimated from weekly returns from month -12 to month -1 15 turnover 0.02 0.01 Average monthly turnover volume from month -12 to month -1 16 debttoprice 0.84 0.32 Short-term plus long-term debt in the prior fiscal year divided by market capitalization at the end of the prior month 17 salestoprice 2.16 0.60 Net sales and revenues in the prior fiscal year divided by market capitalization at the end of the prior month 18 cftoprice 0.14 0.04 Net income plus depreciation, depletion and amortization in the prior fiscal year divided by market capitalization at the end of the prior month 19 earningstoprice 0.04 0.02 Net income in the prior fiscal year divided by market capitalization at the end of the prior month 20 issues_1_12 0.02 0.01 Log growth in split-adjusted shares outstanding from month -12 to month -1 21 fcdispersion -2.05 0.18 Log standard deviation of I/B/E/S EPS forecasts minus log average absolute value of I/B/E/S EPS forecasts from month -12 to month -1 22 grossprofitability 0.30 0.03 Net sales and revenues minus costs of goods sold divided by average total assets in the prior fiscal year Sample size 832 Number of firms with non-missing observations for the excess return and each of the twenty-two characteristics > Investment portfolio performance
“Most importantly, the numbers of the SVM-based model are slightly superior to that of the neural network for both weighting schemes.”
§ Avg Std Definition Excess return [%] 0.51 4.55 Return in excess of the 3-month EURIBOR rate (scaled to the 1-month horizon) 1 size 13.22 0.48 Log market value of equity at the end of the prior month 2 bm -0.55 0.18 Log book value of equity minus log market value of equity at the end of the prior month 3 operatingprofitability 0.06 0.01 Operating profit divided by average total assets in the prior fiscal year 4 totalassetgrowth 0.07 0.04 Log total asset growth in the prior fiscal year 5 ret_2_12 0.09 0.20 Excess return from month -12 to month -2 6 issues_1_36 0.09 0.02 Log growth in split-adjusted shares outstanding from month -36 to month -1 7 accrualschange -0.04 0.01 Working capital accruals (based on Sloan 1996) in the prior fiscal year 8 roa 0.05 0.01 Income before extraordinary items divided by average total assets (return on assets) in the prior fiscal year 9 investment 1.02 0.08 Capital expenditures divided by net sales and revenues in the prior fiscal year 10 ret_1 0.01 0.05 Excess return of the prior month 11 ret_12_36 0.09 0.31 Excess return from month -36 to month -12 12 dy 0.03 0.01 Dividends per share over the prior 12 months divided by price at the end of the prior month 13 beta 0.83 0.10 Market beta, estimated from weekly returns from month -36 to month -1 14 vola 0.32 0.06 Standard deviation, estimated from weekly returns from month -12 to month -1 15 turnover 0.02 0.01 Average monthly turnover volume from month -12 to month -1 16 debttoprice 0.84 0.32 Short-term plus long-term debt in the prior fiscal year divided by market capitalization at the end of the prior month 17 salestoprice 2.16 0.60 Net sales and revenues in the prior fiscal year divided by market capitalization at the end of the prior month 18 cftoprice 0.14 0.04 Net income plus depreciation, depletion and amortization in the prior fiscal year divided by market capitalization at the end of the prior month 19 earningstoprice 0.04 0.02 Net income in the prior fiscal year divided by market capitalization at the end of the prior month 20 issues_1_12 0.02 0.01 Log growth in split-adjusted shares outstanding from month -12 to month -1 21 fcdispersion -2.05 0.18 Log standard deviation of I/B/E/S EPS forecasts minus log average absolute value of I/B/E/S EPS forecasts from month -12 to month -1 22 grossprofitability 0.30 0.03 Net sales and revenues minus costs of goods sold divided by average total assets in the prior fiscal year Sample size 832 Number of firms with non-missing observations for the excess return and each of the twenty-two characteristics > Conclusion
“Before transaction costs Terminal value [€] 70.29 107.18 113.576.00 8.40 9.07 Excess return annualized [%] 22.45 24.93 25.28 8.90 10.67 11.07 Std annualized [%] 18.20 17.82 18.36 17.39 18.50 18.85 Maximum drawdown [%] 51.24 50.12 51.80 44.25 48.87 45.87 Sharpe ratio 1.24 1.41 1.38 0.51 0.58 0.59”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Avg Std Definition Excess return [%] 0.51 4.55 Return in excess of the 3-month EURIBOR rate (scaled to the 1-month horizon) 1 size 13.22 0.48 Log market value of equity at the end of the prior month 2 bm -0.55 0.18 Log book value of equity minus log market value of equity at the end of the prior month 3 operatingprofitability 0.06 0.01 Operating profit divided by average total assets in the prior fiscal year 4 totalassetgrowth 0.07 0.04 Log total asset growth in the prior fiscal year 5 ret_2_12 0.09 0.20 Excess return from month -12 to month -2 6 issues_1_36 0.09 0.02 Log growth in split-adjusted shares outstanding from month -36 to month -1 7 accrualschange -0.04 0.01 Working capital accruals (based on Sloan 1996) in the prior fiscal year 8 roa 0.05 0.01 Income before extraordinary items divided by average total assets (return on assets) in the prior fiscal year 9 investment 1.02 0.08 Capital expenditures divided by net sales and revenues in the prior fiscal year 10 ret_1 0.01 0.05 Excess return of the prior month 11 ret_12_36 0.09 0.31 Excess return from month -36 to month -12 12 dy 0.03 0.01 Dividends per share over the prior 12 months divided by price at the end of the prior month 13 beta 0.83 0.10 Market beta, estimated from weekly returns from month -36 to month -1 14 vola 0.32 0.06 Standard deviation, estimated from weekly returns from month -12 to month -1 15 turnover 0.02 0.01 Average monthly turnover volume from month -12 to month -1 16 debttoprice 0.84 0.32 Short-term plus long-term debt in the prior fiscal year divided by market capitalization at the end of the prior month 17 salestoprice 2.16 0.60 Net sales and revenues in the prior fiscal year divided by market capitalization at the end of the prior month 18 cftoprice 0.14 0.04 Net income plus depreciation, depletion and amortization in the prior fiscal year divided by market capitalization at the end of the prior month 19 earningstoprice 0.04 0.02 Net income in the prior fiscal year divided by market capitalization at the end of the prior month 20 issues_1_12 0.02 0.01 Log growth in split-adjusted shares outstanding from month -12 to month -1 21 fcdispersion -2.05 0.18 Log standard deviation of I/B/E/S EPS forecasts minus log average absolute value of I/B/E/S EPS forecasts from month -12 to month -1 22 grossprofitability 0.30 0.03 Net sales and revenues minus costs of goods sold divided by average total assets in the prior fiscal year Sample size 832 Number of firms with non-missing observations for the excess return and each of the twenty-two characteristics > Machine learning method: Support vector machines
“Note that the aggregate accuracy can equivalently be computed as the number of true classifications (cases in the cells on the confusion matrix's left diagonal) divided by the number of total classifications (cases in any cell of the confusion matrix).”
§ Avg Std Definition Excess return [%] 0.51 4.55 Return in excess of the 3-month EURIBOR rate (scaled to the 1-month horizon) 1 size 13.22 0.48 Log market value of equity at the end of the prior month 2 bm -0.55 0.18 Log book value of equity minus log market value of equity at the end of the prior month 3 operatingprofitability 0.06 0.01 Operating profit divided by average total assets in the prior fiscal year 4 totalassetgrowth 0.07 0.04 Log total asset growth in the prior fiscal year 5 ret_2_12 0.09 0.20 Excess return from month -12 to month -2 6 issues_1_36 0.09 0.02 Log growth in split-adjusted shares outstanding from month -36 to month -1 7 accrualschange -0.04 0.01 Working capital accruals (based on Sloan 1996) in the prior fiscal year 8 roa 0.05 0.01 Income before extraordinary items divided by average total assets (return on assets) in the prior fiscal year 9 investment 1.02 0.08 Capital expenditures divided by net sales and revenues in the prior fiscal year 10 ret_1 0.01 0.05 Excess return of the prior month 11 ret_12_36 0.09 0.31 Excess return from month -36 to month -12 12 dy 0.03 0.01 Dividends per share over the prior 12 months divided by price at the end of the prior month 13 beta 0.83 0.10 Market beta, estimated from weekly returns from month -36 to month -1 14 vola 0.32 0.06 Standard deviation, estimated from weekly returns from month -12 to month -1 15 turnover 0.02 0.01 Average monthly turnover volume from month -12 to month -1 16 debttoprice 0.84 0.32 Short-term plus long-term debt in the prior fiscal year divided by market capitalization at the end of the prior month 17 salestoprice 2.16 0.60 Net sales and revenues in the prior fiscal year divided by market capitalization at the end of the prior month 18 cftoprice 0.14 0.04 Net income plus depreciation, depletion and amortization in the prior fiscal year divided by market capitalization at the end of the prior month 19 earningstoprice 0.04 0.02 Net income in the prior fiscal year divided by market capitalization at the end of the prior month 20 issues_1_12 0.02 0.01 Log growth in split-adjusted shares outstanding from month -12 to month -1 21 fcdispersion -2.05 0.18 Log standard deviation of I/B/E/S EPS forecasts minus log average absolute value of I/B/E/S EPS forecasts from month -12 to month -1 22 grossprofitability 0.30 0.03 Net sales and revenues minus costs of goods sold divided by average total assets in the prior fiscal year Sample size 832 Number of firms with non-missing observations for the excess return and each of the twenty-two characteristics > Machine learning method: Support vector machines
“Aggregate metrics are then calculated as the weighted average of each class' individual metric, taking the number of realized cases within each class as weights.”
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“Random forests (rf) modify Breiman’s (2001) traditional bagging approach.”
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Common risk factors in the returns on stocks and bonds
Fama, E. F., & French, K. R. (1993) · Journal of Financial Economics · doi:10.1016/0304-405x(93)90023-5 · Cited by 25,754 · cited 2×
“Most prominently, Fama and French (1993) propose a multifactor alternative to the CAPM and find that it is better at explaining cross-sectional variation in expected returns than the CAPM.”
BackgroundCAPITAL ASSET PRICES: A THEORY OF MARKET EQUILIBRIUM UNDER CONDITIONS OF RISK*
Sharpe, W. F. (1964) · The Journal of Finance · doi:10.1111/j.1540-6261.1964.tb02865.x · Cited by 19,441 · cited 1×
“For example, the Capital Asset Pricing Model (CAPM) introduced by Sharpe (1964), Lintner (1965), and Mossin (1966) posits that, in equilibrium, a stock’s expected return is solely driven by its sensitivity to a systematic risk factor, i.e., the market risk.”
On Persistence in Mutual Fund Performance
Carhart, M. M. (1997) · The Journal of Finance · doi:10.1111/j.1540-6261.1997.tb03808.x · Cited by 17,283
Filders, R. (1992) · International Journal of Forecasting · doi:10.1016/0169-2070(92)90130-2 · Cited by 16,165
Risk, Return, and Equilibrium: Empirical Tests
Fama, E. F., & MacBeth, J. D. (1973) · Journal of Political Economy · doi:10.1086/260061 · Cited by 14,258 · cited 1×
“This approach typically runs Fama and MacBeth (1973) regressions (FM regressions).”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency
JEGADEESH, N., & TITMAN, S. (1993) · The Journal of Finance · doi:10.1111/j.1540-6261.1993.tb04702.x · Cited by 11,584 · cited 2×
“explain differences in expected returns across stocks as a function of stock-level characteristics, such as size, value, and momentum (Fama and French, 1993; Jegadeesh and Titman, 1993; Lewellen, 2015).”
BackgroundEnsemble methods in machine learning
Dietterich, T. G. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-45014-9_1 · Cited by 8,408
Research works printed but not linked: 2
- Chordia, T., A. Goyal, and A. Saretto. 2017. p-Hacking: Evidence from Two Million Trading Strategies. Swiss Finance Institute Research Paper No. 17–37: 1–53.
- Cochrane, J.H. 2005. Asset Pricing. Revised. Princeton (NJ), US: Princeton University Press.
Cited by
Machine learning and the cross-section of emerging market stock returns
Hanauer, M. X., & Kalsbach, T. (2023) · Emerging Markets Review · doi:10.1016/j.ememar.2023.101022 · Cited by 68
Machine Learning Goes Global: Cross-Sectional Return Predictability in International Stock Markets
Cakici, N., Fieberg, C., Metko, D., & Zaremba, A. (2022) · Journal of Economic Dynamics and Control · doi:10.1016/j.jedc.2023.104725 · Cited by 63
Forecasting Market Crashes via Machine Learning: Evidence from European Stock Markets
Dichtl, H., Drobetz, W., & Otto, T. (2021) · Journal of Financial Stability · doi:10.1016/j.jfs.2022.101099 · Cited by 45
Self-citationStock return prediction with multiple measures using neural network models
Wang, C. E. (2024) · Financial Innovation · doi:10.1186/s40854-023-00608-w · Cited by 35
“Gu et al. (2020), Leippold et al. (2022), and Drobetz and Otto (2021) replace all missing values with the cross-sectional median of each firm-characteristic variable for that month.”
BackgroundMachine learning techniques for cross-sectional equity returns’ prediction
Fieberg, C., Metko, D., Poddig, T., & Loy, T. (2022) · OR Spectrum · doi:10.1007/s00291-022-00693-w · Cited by 47
“This is achieved by applying their research design to other stock markets (see, e.g., Tobek and Hronec 2021; Drobetz and Otto 2021; Leippold et al. 2022; Liu et al. 2022; Rubesam 2022; Lalwani and Meshram 2022, for international applications and applications to individual regions or countries) or…”
Method
Metadata
- Authors
- Drobetz, W., & Otto, T.
- Affiliations
- Universität Hamburg (DE)
- Corresponding author
- Otto, Tizian
- ORCID
- Drobetz, Wolfgang
- Venue
- Journal of Asset Management
- Published
- 2021-11-12
- Volume
- 22
- Issue
- 7
- Pages
- 507-538
- ISSN
- 1470-8272 (ISSN-L)
- 1479-179X
- OpenAlex
- W3213046477
- Cited by
- 61
- References
- 81
- Citations by year
- 2026: 18 · 2025: 7 · 2024: 10 · 2023: 15 · 2022: 8 · 2021: 3
- FWCI
- 7.46
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Journal of Asset Management (publishedVersion, cc-by)
- SSRN Electronic Journal (acceptedVersion)
- Econstor (Econstor) (submittedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Social Sciences › Decision Sciences › Management Science and Operations Research › Risk and Portfolio Optimization
- Keywords
- asset pricing, stock return prediction, machine learning, European stock markets, artificial neural networks, support vector machine, nonlinear effects, price trends, valuation ratios, overfitting, high dimensionality, transaction costs
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-28, under version 3 of the claim definition (prompt extract-v3).
A second model labelled each claim on 2026-09-28 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Empirical asset pricing via machine learning: evidence from the European stock market. https://app.cochat.ai/papers/10.1057/s41260-021-00237-x
- The paper
- Drobetz, W., & Otto, T. (2021). Empirical asset pricing via machine learning: evidence from the European stock market. Journal of Asset Management. https://doi.org/10.1057/s41260-021-00237-x
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.