|
on Forecasting |
| By: | Andrea Carriero; Davide Pettenuzzo; Shubhranshu Shekhar |
| Abstract: | We introduce MACROCAST, a lightweight Time Series Foundation Model (TSFM) for real-time macroeconomic forecasting. Existing TSFMs suffer from data leakage in two forms: temporal contamination, as the model may have seen the realized values of the series it forecasts, and revision bias, as training on fully revised data diverges from the preliminary, vintage-specific releases available to real-time forecasters. MACROCAST is, to our knowledge, the first TSFM that rules out both forms of leakage entirely: at no stage of training is the model exposed to information that would not have been available to a forecaster in real time. We train MACROCAST first on purely synthetic time series in approximately one GPU-day and then fine-tune it on synthetic time series drawn from Bayesian VARs, dynamic factor models, and ARIMA specifications estimated on vintage-specific ALFRED data. Because pretraining uses only simulated data and fine-tuning uses only real-time vintages, no observed future or revised value ever enters the model; each fine-tuning run takes nine minutes. Evaluated on the FRED-MD database in a genuine real-time out-of-sample exercise, MACROCAST improves on the AR(1) benchmark for roughly 80% of series-horizon pairs, matches or surpasses Chronos-2 -- the strongest currently available TSFM -- and outperforms the Bayesian VAR and dynamic factor model benchmarks, all in a data-leakage-free manner. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.28670 |
| By: | Chi, Ta-Chung; Fan, Ting-Han; Ghigliazza, Raffaele; Giannone, Domenico; Wang, Zixuan (Kevin) |
| Abstract: | We forecast the full conditional distribution of macroeconomic outcomes by systematically integrating three key principles: using high-dimensional data with appropriate regularization, adopting rigorous out-of-sample validation procedures, and incorporating nonlinearities. By exploiting the rich information embedded in a large set of macroeconomic and financial predictors, we produce accurate predictions of the entire profile of macroeconomic risk in real time. Our findings show that regularization via shrinkage is essential to control model complexity, while introducing nonlinearities yields limited improvements in predictive accuracy. Out-of-sample validation plays a critical role in selecting model architecture and preventing overfitting. |
| Keywords: | Regularization |
| JEL: | C22 C52 C53 C55 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:20727 |
| By: | Conrad, Christian; Enders, Zeno; Müller, Gernot |
| Abstract: | Under inflation forecast targeting, central banks such as the ECB adjust policy to keep expected inflation on target. We evaluate the ECB’s inflation forecasts: they are unbiased and efficient but contain little information at forecast horizons beyond three quarters. In a New Keynesian model with transmission lags, inflation forecast targeting is indeed effective in stabilizing inflation—provided there is no forward-looking behavior—though the information content of forecasts is unrealistically high. In the presence of forward-looking behavior, the information content declines because monetary policy becomes more effective in meeting the target, but inflation is best stabilized by targeting current inflation. |
| Keywords: | Inflation targeting |
| JEL: | C53 E52 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:20467 |
| By: | Gorodnichenko, Yuriy; Vasudevan, Vittal |
| Abstract: | Using a short- and long-term macroeconomic forecasts, we estimate the cost of the Russian full-scale invasion of Ukraine for countries in Eastern Europe, Caucasus, and Central Asia. Shortly after the Russian attack, the projected cost (cumulative over six years) stood at $2.44 trillion for the region. Professional forecasters predicted a dramatic increase in macroeconomic uncertainty, significant spillover effects, some hysteresis effects as well as a changing nature of business cycles. We also use the war shock to study how professional forecasters acquire and process information. Our results point to state dependence as well as an important role of forward information in shaping macroeconomic outlook of professional forecasters. |
| Keywords: | Conflict; Forecasting; Ukraine; Geoeconomics; Military intervention; Uncertainty |
| JEL: | F51 C53 E3 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:20462 |
| By: | Hyung Joo Kim; Dong Hwan Oh |
| Abstract: | Despite documented heterogeneity in volatility dynamics across the option surface, standard implied volatility forecasting models apply homogeneous parameters throughout. We introduce a machine-learning framework that uses regression trees to partition the surface along both moneyness and maturity dimensions, identifying data-driven regions where distinct forecasting models perform best. Extending the Surface Heterogeneous Autoregressive (SHAR) framework of Dufays, Jacobs, and Rombouts (2025), we develop tree-based SHAR specifications that preserve interpretable structure while allowing model parameters to vary across the surface. Empirical analysis using S&P 500 options demonstrates that the boosted tree-based specification achieves the lowest out-of-sample forecast errors across all horizons, reducing one-month-ahead RMSE by 13 percent versus the benchmark SHAR model. The improvements are statistically significant and particularly pronounced during stress periods. The estimated tree presents economically interpretable segmentation: short-dated options exhibit higher daily persistence but lower monthly persistence than long-dated options, while deep out-of-the-money calls or puts display distinct dynamics from near-the-money contracts. |
| Keywords: | implied volatility forecasting; option surface; machine learning; regression trees; ensemble methods; heterogeneous autoregressive models |
| JEL: | C14 C22 C32 C51 C53 C58 G12 |
| Date: | 2026–07–06 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedgfe:103519 |
| By: | Alessio Brini |
| Abstract: | We ask whether pretrained time series foundation models (TSFMs) improve on established econometric benchmarks for forecasting realized volatility. Using the VOLARE dataset, we conduct the first systematic comparison of nine zero-shot TSFMs against eight econometric specifications, including the Heterogeneous Autoregressive (HAR) family, across 50 assets in equities, foreign exchange, and futures, and three forecast horizons, with formal pairwise and multi-model forecast-comparison tests. Foundation models do not deliver a uniform gain. Pooled losses favor them, but the advantage is concentrated in a few outlier assets; averaging each asset's loss ratio to a well-specified Log-HAR benchmark, so that no single asset dominates, only one small model, Tiny Time Mixers (TTM), beats the benchmark at every horizon, and by a narrow margin. The other foundation models do not improve on Log-HAR, and the econometric benchmarks remain competitive throughout. A Mincer--Zarnowitz recalibration, which removes level and scale bias from every forecast, shows that much of the short-horizon advantage reflects better-scaled forecasts rather than better prediction of volatility dynamics, and only at the monthly horizon does a genuine informational gain remain. Because this edge is thin and even TTM is not best on every asset, a simple equal-weight average of TTM and Log-HAR matches the best single model and enters the Model Confidence Set for 98 to 100\% of assets, more often than either component alone, so a forecaster need not identify the best model for each asset in advance. Our most durable finding is that performance varies so much across foundation-model architectures that choosing the right architecture matters more than the broader choice between foundation and econometric models. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.05291 |
| By: | Marcellino, Massimiliano; Pfarrhofer, Michael |
| Abstract: | We compare homoskedastic and heteroskedastic mixed frequency (MF) vector autoregression and Bayesian additive regression tree (BART) models to assess their relative performance in predicting tail risk. MF-BART is a nonlinear state space model, and we discuss linear approximation approaches to devise computationally efficient estimation algorithms. The models are applied in an out-of-sample backcasting, nowcasting and forecasting exercise for a set of quarterly and monthly macroeconomic variables in Italy. The proposed econometric refinements yield improvements in predictive accuracy. |
| Keywords: | Mixed frequency |
| JEL: | C11 C22 C53 E31 E37 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:20442 |
| By: | Veni Arakelia; Guglielmo Maria Caporale; Mirto M. Gasparinatou; Menelaos Karanasos |
| Abstract: | This paper examines the forecasting of liquidity dynamics in European stock markets by means of traditional econometric models and machine learning techniques. It uses daily data for the DAX, CAC 40, FTSE 100, FTSE MIB, and IBEX 35 over 2010–2026, liquidity being measured by the logarithmic Amihud illiquidity indicator. The empirical framework compares ARIMA models and a dynamic panel specification with Random Forest, Extreme Gradient Boosting (XGBoost), and Support Vector Regression (SVR) within a common rolling one-step-ahead forecasting framework. The results show that liquidity is highly persistent and that the dynamic panel model achieves the lowest forecast errors, although Diebold–Mariano tests indicate no significant predictive advantage over the leading machine learning models. SHAP analysis reveals that trading activity, lagged liquidity, and market uncertainty are the main determinants of liquidity forecasts. The findings highlight the complementary role of explainable machine learning in empirical finance. |
| Keywords: | liquidity dynamics, european stock markets, forecasting, econometric models, machine learning (ML), artificial intelligence (AI) |
| JEL: | C22 C33 C53 G17 |
| Date: | 2026 |
| URL: | https://d.repec.org/n?u=RePEc:ces:ceswps:_12829 |
| By: | Yizhou (Kyle); Kuang |
| Abstract: | Macroeconomic forecasts refer to outcomes that are first released and then revised. A 90 percent interval for the first GDP release, a six-month value, or a latest-value benchmark is not the same uncertainty statement. We ask how revision risk evolves through the release cycle and what can be reported in real time when later-outcome errors are scarce. We decompose later-outcome MSE into preliminary forecast risk, revision risk, and their covariance. In SPF data, first-release to roughly 180-day revisions account for 8.3 percent of later-outcome MSE across real-activity targets, versus 3.6 percent across inflation targets. We show that later-outcome uncertainty is partially identified: released histories give early-error and revision marginals, but not their dependence. This yields a sharp Frechet-Makarov set and motivates direct late calibration, dependence-robust transport, and signed or revision-model transport. Out-of-sample results support method choice rather than a universal transport rule: coverage and stability determine when transport gains are usable. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.05882 |
| By: | Elisabeth Grewenig (KfW, Frankfurt); Klaus Gründler (University of Kassel, ifo Institute, CESifo); Philipp Lergetporer (ifo Institute, CESifo, Technical University of Munich (TUM)); Niklas Potrafke (ifo Institute, CESifo, University of Munich (LMU)); Katharina Werner (ifo Institute, CESifo, Business School Pforzheim); Helen Zeidler (Technical University of Munich (TUM)) |
| Abstract: | Public support for policy interventions depends on citizens’ beliefs about their likely effects. We examine how individuals form such beliefs by studying their predictions of experimental outcomes in a policy-relevant setting, and why their predictions differ from expert benchmarks. We elicit forecasts from 127 professional economists and a representative sample of 6, 200 German households about a large-scale behavioral experiment on education policy (N = 3; 133). Nonexperts predict both average outcomes and treatment effects far less accurately than experts. Prediction accuracy improves with calibrated priors, self-reported effort, and the use of structured reasoning, but remains well below expert levels. We show that scalable design features, including the provision of well-calibrated numerical anchors and monetary incentives to rise effort, improve non-expert predictions, with effects comparable in magnitude to tertiary education or structured reasoning. Our findings have important implications for bridging the ‘expertise gap’ in public discourse. |
| Keywords: | expert forecasts, lay predictions, belief formation, expertise gap, policy support, behavioral experiments |
| JEL: | A11 D83 H52 I22 |
| Date: | 2026–02 |
| URL: | https://d.repec.org/n?u=RePEc:aiw:wpaper:47 |
| By: | Yu Peng; Matloob Khushi; Josiah Poon |
| Abstract: | Cryptocurrency price prediction is a significant challenge in quantitative investment. In recent years, time series models have made significant progress in financial forecasting tasks, especially in the stock market. Despite the growing performance over the past few years, we question the validity of this line of research in cryptocurrency prediction. Specifically, time series models (e.g., LSTM, GRU, and Transformers) are effective at extracting temporal relationships in stock market data. However, in pure price-based cryptocurrency prediction, facing data with extreme volatility and wild swings, time series models have difficulty learning effective information. To validate our claim, we propose CryptoGAT, a lightweight Graph Attention Network that recasts cryptocurrency pure price prediction as a cross-asset graph problem rather than a temporal modeling task. Extensive experiments on real cryptocurrency benchmarks demonstrate that our proposed CryptoGAT outperforms various state-of-the-art forecasting methods with a notable margin. Moreover, we conduct comprehensive empirical studies to explore the fundamental differences exposed by time series models in stock and cryptocurrency prediction: differences in predictability of the signal and cross-asset dependencies. This finding opens up new research directions for the cryptocurrency pure price prediction task and inspires further graph-based exploration in the field. The source code is available at https://github.com/FanBroWell/CryptoGAT |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.27670 |
| By: | Han Feng; Difang Huang; Jue Wang; Zhengjun Zhang |
| Abstract: | We explain the long-standing puzzle of na\"ive diversification with a simple, testable condition: equal weighting is minimum-variance optimal when the forecast-error covariance matrix has a uniform eigenstructure. This "Golden Criterion" drives a two-stage adaptive strategy that dynamically blends naive and optimized weights based on the empirical distance from this condition. Applied to U.S. equity premium forecasting, the method delivers consistent out-of-sample gains in forecast accuracy, utility, and Sharpe ratios. Diversity-driven shrinkage dominates at short horizons, while optimized weights regain their edge at longer horizons, offering clear horizon-dependent guidance for portfolio construction. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.11054 |
| By: | Giovanni Angelini |
| Abstract: | Macroeconomic expectations are usually observed through point forecasts or through asset prices whose mapping into beliefs is model-dependent. This paper uses prediction-market prices to recover high-frequency distributions of short-run macroeconomic beliefs. We construct a panel of Kalshi-implied distributions for CPI and core CPI releases by converting adjacent threshold contracts into probability mass over inflation outcomes. The data reveal market-implied means, uncertainty, and upper-tail probabilities from 30 days to one hour before each release. The market-implied mean contains meaningful forecast information, especially for headline CPI, but the main signal is distributional. Lagged Reuters Poll surprises do not predict systematic deviations of Kalshi means from the current Reuters consensus. By contrast, large lagged surprises are associated with higher implied uncertainty, and positive lagged surprises raise the probability assigned to fixed high-inflation outcomes. In the baseline specification with variable-by-horizon fixed effects, a 0.1 percentage point positive lagged surprise raises the probability of monthly inflation above 0.3 percent by about 4.7 percentage points, even after controlling for the current consensus forecast. In release-level validation tests, Kalshi upper-tail probabilities also predict the realization of high-inflation states, including episodes in which the market-implied mean remains close to the Reuters consensus. The evidence suggests that prediction markets can provide real-time information about inflation risk that is missed by point forecasts. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.30040 |
| By: | Leiva-Leon, Danilo; Sheremirov, Slavik; Tang, Jenny; Zakrajšek, Egon |
| Abstract: | This paper develops an econometric framework for identifying latent factors that provide real-time estimates of supply and demand conditions shaping goods- and services-related price pressures in the U.S. economy. The factors are estimated using category-specific personal consumption expenditures (PCE) data on prices and quantities, using a sign-restricted dynamic factor model that imposes theoretical predictions of the effects of fluctuations in supply and demand on prices and associated quantities through factor loadings. The resulting estimates are used to decompose total PCE inflation into contributions from common factors -- goods demand, goods supply, services demand, services supply, and inflation expectations -- and category-specific idiosyncratic components. Validation exercises demonstrate that the estimated factors provide an informative and coherent narrative of inflation dynamics over time and can be effectively used for forecasting and policy analysis. |
| Keywords: | Inflation; Services; Supply; Demand; Expectations; Dynamic factor models; Sign restrictions |
| JEL: | C11 C32 E31 |
| Date: | 2025–08 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:20574 |
| By: | Aldasoro, Inaki; Hördahl, Peter; Schrimpf, Andreas; Zhu, Sonya |
| Abstract: | Using newly constructed market conditions indicators (MCIs) for three pivotal markets centered around the US dollar (Treasury, foreign exchange, and money markets), we demonstrate that tree-based machine learning (ML) models significantly outperform traditional time-series approaches in predicting the full distribution of future market stress. Through quantile regressions, we show that the random forest method achieves up to 27\% lower quantile loss than autoregressive benchmarks, particularly at longer horizons (up to 12 months). Shapley value analysis reveals that variables related to macro expectations and uncertainty — especially about the monetary policy stance — are important predictors of future tail realizations of market conditions. For individual market segments, the state of the global financial cycle, as well as liquidity conditions, also play important roles. These results highlight the value of ML in forecasting tail risks and identifying systemic vulnerabilities in real time, bridging the gap between high-frequency data and macroeconomic stability frameworks. |
| Keywords: | Shapley value |
| JEL: | G01 C53 G17 G12 G28 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:20439 |
| By: | Sichao He; Yansong Zhang |
| Abstract: | In a deep forecasting pipeline for fat-tailed financial returns at short horizons, which matters more - the backbone architecture or the output head? We compare four modern backbones (TimesNet, DLinear, N-BEATS, iTransformer) under three output heads: a point head, a single-Gaussian density head, and a Gaussian mixture density head with K=4 components. On S and P 500 monthly log-returns (1871-2023) under anchored walk-forward validation, the three heads form a strict gradient: switching from point to Gaussian improves CRPS by about 1.3 percent; switching from Gaussian to mixture adds a further about 2.4 percent. Switching between backbones, in contrast, changes CRPS by less than 1.5 percent on the point-head row and on the backbone-mean axis; density-head backbone spread is larger (up to 5.1 percent on the h=1 Gaussian row, driven by N-BEATS) but the head gradient (3.7 percentage points) still dominates. The Model Confidence Set on squared errors does not exclude any of the 12 variants at the 5 percent level: the head separates them only on distributional metrics (CRPS, pinball, coverage), not on squared error. The mixture head incremental value over a single Gaussian is largest in the highest-volatility regimes (13.9 percent in 1970s stagflation at h=12), confirming the mixture captures tail risk beyond what a unimodal Gaussian can express. The picture is horizon-dependent: the head dominates at short horizons, but at long horizons (h >= 6) the backbone re-takes the lead - an h-split we document against classical baselines (section 5.1). We conclude that on fat-tailed returns at short horizons, the head dominates the backbone, and the mixture distribution adds genuine value over a single Gaussian during crisis periods when risk-management decisions actually matter. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.30037 |
| By: | Dina M Hamed |
| Abstract: | Making informed policy decisions is contingent upon the availability of reliable and timely data. The use of non-traditional data has been shown to be a powerful tool for enabling policymakers to conduct robust nowcasting—the practice of estimating the current period’s economic indicator(s), ahead of official releases, using a wide range of macroeconomic and high-frequency data. This paper showcases how different types of non-traditional data, such as indices extracted from satellite imagery, Google Trends, and flight tracking information, can be leveraged to complement official statistics and monitor economic activity, and how these timely signals can be incorporated into nowcasting models to provide early estimates of key macroeconomic variables in Morocco. The approach is applied to agricultural gross value added, tourism revenues, and the unemployment rate. The results demonstrate that non-traditional data substantially improves nowcasting models by enhancing predictive accuracy and enabling the rapid generation of nowcast estimates prior to the release of official data. |
| Keywords: | Nowcasting; Macroeconomic Forecasting; Non-traditional data; Satellite Imagery; Google Trends; Tourism Revenues; Agriculture GVA; Unemployment Rate; Machine learning; Morocco |
| Date: | 2026–06–05 |
| URL: | https://d.repec.org/n?u=RePEc:imf:imfwpa:2026/108 |
| By: | Xinxiang Guo; Yingkai Li; Yifen Mu |
| Abstract: | Decision-makers often rely on multiple probabilistic forecasts that are individually calibrated but need not be fully informative. We develop a framework for aggregating such forecasts when the decision-maker knows only that experts satisfy calibration. We show that the joint distribution of calibrated forecasts can contain decision-relevant information that is unavailable from any single expert, so the standard optimal-in-hindsight (OIH) benchmark may substantially understate attainable performance. To formalize this idea, we introduce a robust max-min benchmark: the best payoff a decision-maker can guarantee against all profile-wise conditional-mean mappings compatible with calibration. This benchmark is tractable, admits a linear-programming formulation, and dominates the OIH benchmark up to calibration error. It can nevertheless be strictly below the Bayesian benchmark, clarifying the value of knowing experts' information structures. Finally, we provide online algorithms that attain the robust benchmark under forecast-only feedback and stronger contextual benchmarks under state feedback. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.31020 |
| By: | Junjie Guo |
| Abstract: | Predict-then-optimize systems usually compress uncertainty into a point forecast and then solve a downstream optimization problem as if the forecast were reliable. Distributionally robust optimization (DRO) offers protection against misspecification, but the ambiguity set is often centered at historical samples and uses a fixed radius. We propose \emph{learned predictive ambiguity sets} (LPAS): a deep contextual model outputs a finite nominal scenario distribution, a state-dependent Wasserstein radius, and optionally an anisotropic ground metric. These outputs define a contextual ambiguity set that feeds a DRO decision layer. The radius is trained by a combination of conditional quantile calibration, size regularization, and downstream decision loss, so that robustness is adaptive rather than globally fixed. We derive the finite dual form used by the decision layer, present a staged training algorithm, and evaluate the method on distributionally robust portfolio optimization with 20 S&P 500 constituents from 2018--2026. The proposed method substantially improves over equal-weight, predict-then-optimize, and historical Wasserstein DRO baselines, achieving 26.28% annualized return, Sharpe ratio 1.30, final wealth 1.61, and lower tail loss than a deep fixed-radius DRO baseline while using a smaller average radius. The results show that learned ambiguity radii can recover most of the performance of strong fixed-radius DRO while reducing unnecessary conservatism and improving regime adaptivity. |
| Date: | 2026–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2607.09820 |
| By: | Miguel Acosta; Yeji Sung |
| Abstract: | Firms frequently revise not only their expectations, but also how uncertain they feel about those expectations. Using the U.S. Survey of Business Uncertainty, we study perceived uncertainty about firms’ own sales and employment growth. Reported uncertainty rises after larger revisions to firms’ point forecasts, with the strongest response to the most recent revision. This recency pattern remains visible outside elevated sectoral-volatility episodes. We develop a model in which agents learn about a constant-volatility process but recall older observations noisily. Noisy recall gives recent surprises disproportionate influence, even when objective volatility is constant. |
| JEL: | D84 E32 E71 G41 |
| Date: | 2026–07–10 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fedfwp:103549 |
| By: | Aquilina, Matteo; Araujo, Douglas; Gelos, Gaston; Park, Taejin; Perez-Cruz, Fernando |
| Abstract: | Predicting financial market stress has long proven to be a largely elusive goal. Advances in artificial intelligence and machine learning offer new possibilities to tackle this problem, given their ability to handle large datasets and unearth hidden nonlinear patterns. In this paper, we develop a new approach based on a combination of a recurrent neural network (RNN) and a large language model. Focusing on deviations from triangular arbitrage parity (TAP) in the Euro-Yen currency pair, our RNN produces interpretable daily forecasts of market dysfunction 60 business days ahead. To address the “black box†limitations of RNNs, our model assigns data-driven, time-varying weights to the input variables, making its decision process transparent. These weights serve a dual purpose. First, their evolution in and of itself provides early signals of latent changes in market dynamics. Second, when the network forecasts a higher probability of market dysfunction, these variable-specific weights help identify relevant market variables that we use to prompt an LLM to search for relevant information about potential market stress drivers. |
| JEL: | G14 G15 G17 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:20768 |
| By: | Haji Mohamad Zubir, Ahmad Shauqi bin; Mohd Nasir, Muhammad Luqman bin |
| Abstract: | Trading volume has forecast volatility in half a century of research, yet risk models hold capital at extreme quantiles the volume literature never scores. We evaluate the expected and unexpected components of trading volume inside a layered tail risk architecture, a volatility filter beneath an extreme value model for standardized exceedances, for 300 liquid Bursa Malaysia firms over 467, 148 evaluation days from 2018 to 2025, with every model re-estimated annually in real time and forecasts ranked by strictly consistent scoring functions. Four results emerge. Unexpected volume improves 99th and 99.5th percentile forecasts by about a tenth of a percent of the quantile loss, on 58 percent of days, at unchanged coverage and capital, robust to a pre-committed battery including a full pipeline permutation placebo. The signal is layer specific: surprise volume works entirely through the volatility filter and adds nothing to the exceedance scale at any threshold, the exclusion that return subordination implies, while expected volume compresses the extreme tail from within, the signature of market depth. The gains concentrate in 2021 through 2025, dating the signal's value to a documented transformation of the trading environment. And direct censored likelihood quantification shows this market's price limits shift implied extreme quantiles by half a basis point, licensing standard architectures by measurement rather than assumption. Volume belongs in risk systems, in a specific place, at a measurable price. |
| Keywords: | Trading volume; Value at risk; Extreme value theory; Forecast evaluation; Market depth; Price limits |
| JEL: | C1 G12 |
| Date: | 2026–07–22 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:130162 |
| By: | Malliaropulos, Dimitris; Passari, Evgenia; Petroulakis, Filippos |
| Abstract: | We show that text-based indicators of supply and demand disturbances in commodity markets provide distinct information about future inflation movements relative to existing predictors, inflation expectations and survey forecasts. Specifically, we document that demand-side disturbances play a significantly larger role in prediction because they typically lead to uniform increases in quantities and prices of goods across the consumer basket, resulting in a clear and positive relationship between commodity prices and overall inflation. Supply-side disturbances matter in particular circumstances, for instance during the recent period of the pandemic and geopolitical shocks. In terms of magnitudes, the commodity-specific indicators reduce out-of-sample inflation forecast errors by up to 30 percent. We finally apply our indexes to the inflation decomposition framework of Blanchard and Bernanke (2023) and corroborate their finding that the bulk of pandemic-era inflation can be attributed to commodity supply disruptions, resulting in price increases in goods markets. |
| JEL: | C19 E31 E37 Q02 |
| Date: | 2025–07 |
| URL: | https://d.repec.org/n?u=RePEc:cpr:ceprdp:20404 |