|
on Forecasting |
| By: | Santhi Bharath Punati; Sandeep Kanta; Udaya Bhasker Cheerala; Madhusudan G Lanjewar; Praveen Damacharla |
| Abstract: | Accurate multi-horizon retail forecasts are critical for inventory and promotions. We present a novel study of weekly Walmart sales (45 stores, 2010--2012) using a Temporal Fusion Transformer (TFT) that fuses static store identifiers with time-varying exogenous signals (holidays, CPI, fuel price, temperature). The pipeline produces 1--5-week-ahead probabilistic forecasts via Quantile Loss, yielding calibrated 90\% prediction intervals and interpretability through variable-selection networks, static enrichment, and temporal attention. On a fixed 2012 hold-out dataset, TFT achieves an RMSE of \$57.9k USD per store-week and an $R^2$ of 0.9875. Across a 5-fold chronological cross-validation, the averages are RMSE = \$64.6k USD and $R^2$ = 0.9844, outperforming the XGB, CNN, LSTM, and CNN-LSTM baseline models. These results demonstrate practical value for inventory planning and holiday-period optimization, while maintaining model transparency. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.00552 |
| By: | Shovon Sengupta; Sunny Kumar Singh; Tanujit Chakraborty |
| Abstract: | Accurate macroeconomic forecasting has become harder amid geopolitical disruptions, policy reversals, and volatile financial markets. Conventional vector autoregressions (VARs) overfit in high dimensional settings, while threshold VARs struggle with time varying interdependencies and complex parameter structures. We address these limitations by extending the Sims Zha Bayesian VAR with exogenous variables (SZBVARx) to incorporate domain-informed shrinkage and four newspaper based uncertainty shocks such as economic policy uncertainty, geopolitical risk, US equity market volatility, and US monetary policy uncertainty. The framework improves structural interpretability, mitigates dimensionality, and imposes empirically guided regularization. Using G7 data, we study spillovers from uncertainty shocks to five core variables (unemployment, real broad effective exchange rates, short term rates, oil prices, and CPI inflation), combining wavelet coherence (time frequency dynamics) with nonlinear local projections (state dependent impulse responses). Out-of-sample results at 12 and 24 month horizons show that SZBVARx outperforms 14 benchmarks, including classical VARs and leading machine learning models, as confirmed by Murphy difference diagrams, multivariate Diebold Mariano tests, and Giacomini White predictability tests. Credible Bayesian prediction intervals deliver robust uncertainty quantification for scenario analysis and risk management. The proposed SZBVARx offers G7 policymakers a transparent, well calibrated tool for modern macroeconomic forecasting under pervasive uncertainty. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.23347 |
| By: | Giulia Iadisernia; Carolina Camassa |
| Abstract: | We evaluate whether persona-based prompting improves Large Language Model (LLM) performance on macroeconomic forecasting tasks. Using 2, 368 economics-related personas from the PersonaHub corpus, we prompt GPT-4o to replicate the ECB Survey of Professional Forecasters across 50 quarterly rounds (2013-2025). We compare the persona-prompted forecasts against the human experts panel, across four target variables (HICP, core HICP, GDP growth, unemployment) and four forecast horizons. We also compare the results against 100 baseline forecasts without persona descriptions to isolate its effect. We report two main findings. Firstly, GPT-4o and human forecasters achieve remarkably similar accuracy levels, with differences that are statistically significant yet practically modest. Our out-of-sample evaluation on 2024-2025 data demonstrates that GPT-4o can maintain competitive forecasting performance on unseen events, though with notable differences compared to the in-sample period. Secondly, our ablation experiment reveals no measurable forecasting advantage from persona descriptions, suggesting these prompt components can be omitted to reduce computational costs without sacrificing accuracy. Our results provide evidence that GPT-4o can achieve competitive forecasting accuracy even on out-of-sample macroeconomic events, if provided with relevant context data, while revealing that diverse prompts produce remarkably homogeneous forecasts compared to human panels. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.02458 |
| By: | Kaito Takano; Masanori Hirano; Kei Nakagawa |
| Abstract: | Accurately forecasting central bank policy decisions, particularly those of the Federal Open Market Committee(FOMC) has become increasingly important amid heightened economic uncertainty. While prior studies have used monetary policy texts to predict rate changes, most rely on static classification models that overlook the deliberative nature of policymaking. This study proposes a novel framework that structurally imitates the FOMC's collective decision-making process by modeling multiple large language models(LLMs) as interacting agents. Each agent begins with a distinct initial belief and produces a prediction based on both qualitative policy texts and quantitative macroeconomic indicators. Through iterative rounds, agents revise their predictions by observing the outputs of others, simulating deliberation and consensus formation. To enhance interpretability, we introduce a latent variable representing each agent's underlying belief(e.g., hawkish or dovish), and we theoretically demonstrate how this belief mediates the perception of input information and interaction dynamics. Empirical results show that this debate-based approach significantly outperforms standard LLMs-based baselines in prediction accuracy. Furthermore, the explicit modeling of beliefs provides insights into how individual perspectives and social influence shape collective policy forecasts. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.02469 |
| By: | Carlos Segura-Rodriguez (Department of Economic Research, Central Bank of Costa Rica) |
| Abstract: | This study proposes a methodology for forecasting inflation in Costa Rica based on a disaggregated analysis of the 289 items that comprise the Consumer Price Index (CPI). ARIMA models are used for most items, while ARIMAX models —which incorporate exogenous variables— are applied to those with higher weights and more volatile prices. The inclusion of specific information, such as the exchange rate, international commodity prices, and weekly agricultural prices, significantly improves forecast accuracy over short-term horizons. The disaggregated approach consistently outperforms more aggregated models or those without exogenous variables by reducing errors in sensitive items such as food, fuel, regulated goods, and products priced in U.S. dollars. The results highlight the value of integrating additional information into forecasting strategies based on disaggregated data and suggest that this methodology can effectively complement the short-term inflation forecasting models currently used by the Central Bank. ***Resumen: Este estudio propone una metodología para el pronóstico de la inflación en Costa Rica basada en el análisis desagregado de los 289 artículos que conforman el Índice de Precios al Consumidor (IPC). Se emplean modelos ARIMA para la mayoría de los artículos y modelos ARIMAX —que incorporan variables exógenas— para aquellos con mayor ponderación y precios más volátiles. La inclusión de información específica, como el tipo de cambio, precios internacionales de materias primas y precios agrícolas semanales, mejora significativamente la precisión de los pronósticos en horizontes de corto plazo. El enfoque desagregado supera sistemáticamente a modelos más agregados o sin variables exógenas, al reducir errores en productos sensibles como alimentos, combustibles, bienes regulados y aquellos cotizados en dólares. Los resultados evidencian el valor de integrar información adicional en estrategias de pronóstico basadas en datos desagregados, y sugieren que esta metodología puede complementar eficazmente los modelos de pronóstico de corto plazo utilizados por el Banco Central. |
| Keywords: | Stress Tests, Yield Curve Estimation, Financial Crisis, Pruebas de tensión, Curvas de rendimiento, Crisis financieras |
| JEL: | G21 G28 C63 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:apk:doctra:2509 |
| By: | Jos\'e \'Angel Islas Anguiano; Andr\'es Garc\'ia-Medina |
| Abstract: | In this note, we compare Bitcoin trading performance using two machine learning models-Light Gradient Boosting Machine (LightGBM) and Long Short-Term Memory (LSTM)-and two technical analysis-based strategies: Exponential Moving Average (EMA) crossover and a combination of Moving Average Convergence/Divergence with the Average Directional Index (MACD+ADX). The objective is to evaluate how trading signals can be used to maximize profits in the Bitcoin market. This comparison was motivated by the U.S. Securities and Exchange Commission's (SEC) approval of the first spot Bitcoin exchange-traded funds (ETFs) on 2024-01-10. Our results show that the LSTM model achieved a cumulative return of approximately 65.23% in under a year, significantly outperforming LightGBM, the EMA and MACD+ADX strategies, as well as the baseline buy-and-hold. This study highlights the potential for deeper integration of machine learning and technical analysis in the rapidly evolving cryptocurrency landscape. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.00665 |
| By: | Bin Chen; Yuefeng Han; Qiyang Yu |
| Abstract: | In this paper, we consider diffusion index forecast with both tensor and non-tensor predictors, where the tensor structure is preserved with a Canonical Polyadic (CP) tensor factor model. When the number of non-tensor predictors is small, we study the asymptotic properties of the least-squared estimator in this tensor factor-augmented regression, allowing for factors with different strengths. We derive an analytical formula for prediction intervals that accounts for the estimation uncertainty of the latent factors. In addition, we propose a novel thresholding estimator for the high-dimensional covariance matrix that is robust to cross-sectional dependence. When the number of non-tensor predictors exceeds or diverges with the sample size, we introduce a multi-source factor-augmented sparse regression model and establish the consistency of the corresponding penalized estimator. Simulation studies validate our theoretical results and an empirical application to US trade flows demonstrates the advantages of our approach over other popular methods in the literature. |
| Date: | 2025–11 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2511.02235 |
| By: | Ollie Olby; Rory Baggott; Namid Stillman |
| Abstract: | The recent application of deep learning models to financial trading has heightened the need for high fidelity financial time series data. This synthetic data can be used to supplement historical data to train large trading models. The state-of-the-art models for the generative application often rely on huge amounts of historical data and large, complicated models. These models range from autoregressive and diffusion-based models through to architecturally simpler models such as the temporal-attention bilinear layer. Agent-based approaches to modelling limit order book dynamics can also recreate trading activity through mechanistic models of trader behaviours. In this work, we demonstrate how a popular agent-based framework for simulating intraday trading activity, the Chiarella model, can be combined with one of the most performant deep learning models for forecasting multi-variate time series, the TABL model. This forecasting model is coupled to a simulation of a matching engine with a novel method for simulating deleted order flow. Our simulator gives us the ability to test the generative abilities of the forecasting model using stylised facts. Our results show that this methodology generates realistic price dynamics however, when analysing deeper, parts of the markets microstructure are not accurately recreated, highlighting the necessity for including more sophisticated agent behaviors into the modeling framework to help account for tail events. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.22685 |
| By: | Aryan Ranjan |
| Abstract: | We present a systematic trading framework that forecasts short-horizon market risk, identifies its underlying drivers, and generates alpha using a hybrid machine learning ensemble built to trade on the resulting signal. The framework integrates neural networks with tree-based voting models to predict five-day drawdowns in the S&P 500 ETF, leveraging a cross-asset feature set spanning equities, fixed income, foreign exchange, commodities, and volatility markets. Interpretable feature attribution methods reveal the key macroeconomic and microstructural factors that differentiate high-risk (crash) from benign (non-crash) weekly regimes. Empirical results show a Sharpe ratio of 2.51 and an annualized CAPM alpha of +0.28, with a market beta of 0.51, indicating that the model delivers substantial systematic alpha with limited directional exposure during the 2005--2025 backtest period. Overall, the findings underscore the effectiveness of hybrid ensemble architectures in capturing nonlinear risk dynamics and identifying interpretable, potentially causal drivers, providing a robust blueprint for machine learning-driven alpha generation in systematic trading. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.22348 |
| By: | Avirup Chakraborty |
| Abstract: | The European Union Emissions Trading System (EU ETS), the worlds largest cap-and-trade carbon market, is central to EU climate policy. This study analyzes its efficiency, price behavior, and market structure from 2010 to 2020. Using an AR-GARCH framework, we find pronounced price clustering and short-term return predictability, with 60.05 percent directional accuracy and a 70.78 percent hit rate within forecast intervals. Network analysis of inter-country transactions shows a concentrated structure dominated by a few registries that control most high-value flows. Country-specific log-log regressions of price on traded quantity reveal heterogeneous and sometimes positive elasticities exceeding unity, implying that trading volumes often rise with prices. These results point to persistent inefficiencies in the EU ETS, including partial predictability, asymmetric market power, and unconventional price-volume relationships, suggesting that while the system contributes to decarbonization, its trading dynamics and price formation remain imperfect. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.22341 |
| By: | Matt Salehi (Mehdi) |
| Abstract: | This study explored how advanced budgeting techniques and economic indicators influence funding levels and strategic alignment in California Community Colleges (CCCs). Despite widespread implementation of budgeting reforms, many CCCs continue to face challenges aligning financial planning with institutional missions, particularly in supporting diversity, equity, and inclusion (DEI) initiatives. The study used a quantitative correlational design, analyzing 30 years of publicly available economic data, including unemployment rates, GDP growth, and CPI, in relation to CCC funding trends. Results revealed a strong positive correlation between GDP growth and CCC funding levels, as well as between CPI and funding levels, underscoring the predictive value of macroeconomic indicators in budget planning. These findings emphasize the need for educational leaders to integrate economic forecasting into budget planning processes to safeguard institutional effectiveness and sustain programs serving underrepresented student populations. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.26035 |
| By: | Kevin Moran; Dalibor Stevanovic; Stéphane Surprenant |
| Abstract: | This paper discusses the usefulness of risk scenarios—forecasts conditional on specific future paths for economic variables and shocks—for monitoring the Canadian economy. To do so, we use a vector autoregressive (VAR) approach to produce macroeconomic forecasts conditional on four risk scenarios: high oil prices, a US recession, a tight labor market, and a restrictive monetary policy. The results show that these scenarios represent significant risk factors for the evolution of the Canadian economy. In particular, the high-oil-price scenario is beneficial for the Canadian economy, while a US recession induces a significant slowdown. The very tight labor market scenario leads to additional price increases relative to an unconditional forecast, and the restrictive monetary policy scenario increases the unemployment rate while lowering the inflation rate slightly. |
| Keywords: | Econometric and statistical methods; Business fluctuations and cycles; Monetary policy |
| JEL: | E32 F41 F44 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:bca:bocawp:25-28 |
| By: | Nikolas Anic; Andrea Barbon; Ralf Seiz; Carlo Zarattini |
| Abstract: | This paper investigates whether large language models (LLMs) can improve cross-sectional momentum strategies by extracting predictive signals from firm-specific news. We combine daily U.S. equity returns for S&P 500 constituents with high-frequency news data and use prompt-engineered queries to ChatGPT that inform the model when a stock is about to enter a momentum portfolio. The LLM evaluates whether recent news supports a continuation of past returns, producing scores that condition both stock selection and portfolio weights. An LLM-enhanced momentum strategy outperforms a standard long-only momentum benchmark, delivering higher Sharpe and Sortino ratios both in-sample and in a truly out-of-sample period after the model's pre-training cut-off. These gains are robust to transaction costs, prompt design, and portfolio constraints, and are strongest for concentrated, high-conviction portfolios. The results suggest that LLMs can serve as effective real-time interpreters of financial news, adding incremental value to established factor-based investment strategies. |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2510.26228 |
| By: | Barry Eichengreen; Raul Razo-Garcia |
| Abstract: | In a paper 20 years ago, we analyzed the evolution of the international monetary system over the preceding 20 years and projected its evolution 20 years into the future, on the assumption of unchanged transition probabilities. Here we compare those projections with outcomes and provide new projections, again 20 years into the future. Although the world as a whole has seen financial opening and movement away from intermediate exchange rate regimes, as projected, movement has been slower than projected on the basis of observed transition probabilities in the 20 years preceding our forecast. New projections again based on unchanged transition probabilities but allowing countries to shift between advanced, emerging and developing country groupings and reclassifying exchange rate regimes to accord with current practice again suggest that policy regimes will be modestly different in 2045 than today. There will be a continued decline in intermediate exchange rate arrangements, and gains for hard pegs, as emerging markets move in this direction, and for more freely floating rates, driven by developing countries. There will be a further increase in the share of countries with open capital accounts, driven by emerging markets and developing countries. |
| JEL: | F0 F33 |
| Date: | 2025–10 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:34416 |