Macroeconomic Variables

Ultimate Forward Rate Prediction and its Application to Bond Yield Forecasting: A Machine Learning Perspective ArXiv ID: 2601.00011 “View on arXiv” Authors: Jiawei Du, Yi Hong Abstract This study focuses on forecasting the ultimate forward rate (UFR) and developing a UFRbased bond yield prediction model using data from Chinese treasury bonds and macroeconomic variables spanning from December 2009 to December 2024. The de Kort-Vellekooptype methodology is applied to estimate the UFR, incorporating the optimal turning parameter determination technique proposed in this study, which helps mitigate anomalous fluctuations. In addition, both linear and nonlinear machine learning techniques are employed to forecast the UFR and ultra-long-term bond yields. The results indicate that nonlinear machine learning models outperform their linear counterparts in forecasting accuracy. Incorporating macroeconomic variables, particularly price index-related variables, significantly improves the accuracy of predictions. Finally, a novel UFR-based bond yield forecasting model is developed, demonstrating superior performance across different bond maturities. ...

On the macroeconomic fundamentals of long-term volatilities and dynamic correlations in COMEX copper futures ArXiv ID: 2409.08355 “View on arXiv” Authors: Unknown Abstract This paper examines the influence of low-frequency macroeconomic variables on the high-frequency returns of copper futures and the long-term correlation with the S&P 500 index, employing GARCH-MIDAS and DCC-MIDAS modeling frameworks. The estimated results of GARCH-MIDAS show that realized volatility (RV), level of interest rates (IR), industrial production (IP) and producer price index (PPI), volatility of Slope, PPI, consumer sentiment index (CSI), and dollar index (DI) have significant impacts on Copper futures returns, among which PPI is the most efficient macroeconomic variable. From comparison among DCC-GARCH and DCC-MIDAS model, the added MIDAS filter of PPI improves the model fitness and have better performance than RV in effecting the long-run relationship between Copper futures and S&P 500. ...

Lower Bounds of Uncertainty of Observations of Macroeconomic Variables and Upper Limits on the Accuracy of Their Forecasts ArXiv ID: 2408.04644 “View on arXiv” Authors: Unknown Abstract This paper defines theoretical lower bounds of uncertainty of observations of macroeconomic variables that depend on statistical moments and correlations of random values and volumes of market trades. Any econometric assessments of macroeconomic variables have greater uncertainty. We consider macroeconomic variables as random that depend on random values and volumes of trades. To predict random macroeconomic variables, one should forecast their probabilities. Upper limits on the accuracy of the forecasts of probabilities of macroeconomic variables, prices, and returns depend on the number of predicted statistical moments. We consider economic obstacles that limit by the first two the number of predicted statistical moments. The accuracy of any forecasts of probabilities of random macroeconomic variables, prices, returns, and market trades doesn’t exceed the accuracy of Gaussian approximations. Any forecasts of macroeconomic variables have uncertainty higher than one determined by predictions of coefficients of variation of random values and volumes of trades. ...

Theoretical Economics as Successive Approximations of Statistical Moments ArXiv ID: 2310.05971 “View on arXiv” Authors: Unknown Abstract This paper studies the links between the descriptions of macroeconomic variables and statistical moments of market trade, price, and return. The randomness of market trade values and volumes during the averaging interval Δ results in the random properties of price and return. We describe how averages and volatilities of price and return depend on the averages, volatilities, and correlations of market trade values and volumes. The averages, volatilities, and correlations of market trade, price, and return can behave randomly during the long interval Δ2»Δ. To describe their statistical properties during the long interval Δ2, we introduce the secondary averaging procedure of trade, price, and return. We explain why, in the coming years, predictions of market-based probabilities of price and return will be limited by Gaussian distributions. We discuss the roots of the internal weakness of the commonly used hedging tool, Value-at-Risk, that cannot be solved and remains the source of additional risks and losses. One should consider theoretical economics as a set of successive approximations, each of which describes the next array of the n-th statistical moments of market trades, price, return, and macroeconomic variables, which are repeatedly averaged during the sequence of increasing time intervals. ...

Retail Demand Forecasting: A Comparative Study for Multivariate Time Series ArXiv ID: 2308.11939 “View on arXiv” Authors: Unknown Abstract Accurate demand forecasting in the retail industry is a critical determinant of financial performance and supply chain efficiency. As global markets become increasingly interconnected, businesses are turning towards advanced prediction models to gain a competitive edge. However, existing literature mostly focuses on historical sales data and ignores the vital influence of macroeconomic conditions on consumer spending behavior. In this study, we bridge this gap by enriching time series data of customer demand with macroeconomic variables, such as the Consumer Price Index (CPI), Index of Consumer Sentiment (ICS), and unemployment rates. Leveraging this comprehensive dataset, we develop and compare various regression and machine learning models to predict retail demand accurately. ...

Action-State Dependent Dynamic Model Selection ArXiv ID: 2307.04754 “View on arXiv” Authors: Unknown Abstract A model among many may only be best under certain states of the world. Switching from a model to another can also be costly. Finding a procedure to dynamically choose a model in these circumstances requires to solve a complex estimation procedure and a dynamic programming problem. A Reinforcement learning algorithm is used to approximate and estimate from the data the optimal solution to this dynamic programming problem. The algorithm is shown to consistently estimate the optimal policy that may choose different models based on a set of covariates. A typical example is the one of switching between different portfolio models under rebalancing costs, using macroeconomic information. Using a set of macroeconomic variables and price data, an empirical application to the aforementioned portfolio problem shows superior performance to choosing the best portfolio model with hindsight. ...