International Journal of Economics and Finance, Issue: Vol.18, No.8

Forecasting Weekly S&P 500 Returns Using Machine Learning: Evidence from Technical and Volume-Based Indicators

Wed, 08 Jul 2026 06:34:31 +0000

Forecasting stock market returns remains a central challenge in finance, and much of the existing literature has relied on linear econometric models, which often struggle to capture nonlinear and time-varying patterns in equity markets. Prior studies have shown mixed evidence regarding the predictive value of technical indicators, leaving uncertainty about whether they contain meaningful information for short-term forecasting. This study addresses that gap by examining the predictability of weekly S&P 500 returns using traditional market-based indicators combined with modern machine learning methods. Weekly price and volume data from January 2000 to October 2025 are used to evaluate whether momentum, moving averages, volatility, and trading volume provide forecasting power for aggregate returns. Two ensemble algorithms, Random Forest and Histogram Based Gradient Boosting, are applied within an expanding window validation design. Results indicate that Gradient Boosting explains approximately 70% of the variation in weekly returns, demonstrating that adaptive learning approaches can reveal meaningful short-term market dynamics.

Trade Openness, Exchange Rate Volatility and FDI Inflows in Italy and the European Union

Wed, 22 Jul 2026 04:16:04 +0000

This study examines how trade openness and exchange rate volatility influence foreign direct investment (FDI) inflows in Italy and the European Union over the period 2006–2022. Using an Autoregressive Distributed Lag (ARDL) model, the analysis explores both long-term and short-term dynamics among FDI, trade openness and the EUR/USD exchange rate, capturing pre- and post-pandemic developments. The findings indicate that sustained trade liberalization and currency stability are key drivers of long-term FDI inflows, while short-term effects are limited, suggesting that temporary policy changes and market fluctuations have minimal impact on investment decisions. These results highlight the importance of stable macroeconomic conditions and open trade policies in enhancing investor confidence. The study provides relevant implications for policymakers and business stakeholders, emphasizing the role of consistent economic strategies in strengthening the attractiveness of Italy and the European Union for foreign investment.

A Behavioral Scorecard Model Using Survival Analysis

Thu, 30 Jul 2026 02:56:43 +0000

Credit risk assessment is central to modern lending because it supports default prevention and improves financial decision-making. Traditional credit scorecards often rely on binary logistic regression, which is simple and interpretable but limited in that it does not model the timing of default. This paper develops a monthly behavioral scorecard framework that combines discrete-time logistic regression with survival analysis. Using a large longitudinal dataset of 30-year fixed-rate mortgages from Freddie Mac covering 2018-2024, the study constructs an exploded panel representation to capture time-varying risk profiles. To address the computational burden of very large panels, a backward progressive weighting scheme reduces the effective sample size while preserving statistical power. The model integrates static borrower attributes, dynamic loan lifecycle variables transformed with multivariate adaptive regression splines (MARS) to capture nonlinear effects, and time-varying macroeconomic indicators to reflect systemic volatility. A calibration method is then presented to convert discrete monthly hazard rates into cumulative default probabilities, followed by an offset adjustment to produce a points-to-double-the-odds (PDO) behavioral scorecard. Backtesting across in-sample, holdout, and out-of-time samples demonstrates strong discrimination, with in-sample AUC of 0.82 and out-of-time AUC of 0.70. The resulting framework supports practical, lifecycle-based credit interventions and regulatory capital applications.

The Brazilian Space Sectoral Innovation System: State Preponderance and Institutional Concentration

Thu, 30 Jul 2026 03:01:15 +0000

This paper examines how research resources are distributed across institutional actors in the Brazilian space sector, using funding allocation as an indicator of the structure of the innovation system. Drawing on data from the National Council for Scientific and Technological Development (CNPq) covering 15,109 scholarships between 2005 and 2024, we analyze how resources are allocated across universities, government research institutions, private companies, and foreign organizations. To assess patterns of concentration, we apply the Herfindahl–Hirschman Index (HHI) at both the system and category levels. The results reveal a dual structure. While Brazilian universities account for most scholarships, resource allocation within this category is relatively dispersed. In contrast, government institutions exhibit high levels of concentration, with a small number of organizations acting as focal points of capability accumulation. Private-sector participation remains limited and largely indirect, relying on public intermediaries. These findings indicate that the Brazilian space sector is characterized by centralized coordination within the public sector combined with distributed knowledge production across universities. This configuration reinforces the State’s central role not only as funder but also as organizer of the system, while creating structural vulnerabilities associated with dependence on public funding. The paper contributes by showing how funding distribution can be used to reveal the structural configuration of state-led innovation systems.

The Determinants of the Price of Live Cattle in Brazil

Sun, 02 Aug 2026 05:23:50 +0000

This paper aims to evaluate the factors that influence the future price of live cattle in the Brazilian market. To this end, we employ an autoregressive distributed lag (ARDL) approach because of its ability to handle variables with different orders of integration. Additionally, the ARDL model enables the distinction between short-term and long-term effects. We use the international price of live cattle, macroeconomic variables (e.g., exchange and interest rates), and the price of inputs (e.g., corn and wheat) as potential explanatory variables. Our findings indicate that the international price of live cattle does not significantly impact the formation of the domestic price in the Brazilian market. Conversely, the dynamics between domestic supply, represented by slaughter cattle, and domestic demand, represented by the economic activity index, are key drivers of the future price of live cattle in Brazil.