The use of recommender systems to assist in the provision of financial asset and portfolio recommendations to investors is increasing, spanning a wide range of algorithms and techniques. Several strategies have been devised for the evaluation of financial asset recommendations, with the two most prominent perspectives measuring, respectively, (a) the money customers could obtain if they followed the recommendations (profitability-based evaluation) and (b) the ability of models to predict future customer investments (transaction-based evaluation). If customers are effective investors, we would expect these two perspectives to be positively correlated. In this article, we explore the actual relationship between these two families of metrics. Theoretically, we prove that these perspectives are independent. Furthermore, we perform experiments over a large-scale financial recommendation dataset with real customer investment transactions. Surprisingly, we find that transaction and profitability-based metrics are, in fact, negatively correlated. Moreover, algorithms that actively learn from past customer transactions might lose money in the mid-term. A thorough analysis of model performance and customer transaction patterns over time shows that this is due to customers failing to consistently beat the market with their investments, with time appearing as an important confounding variable-since the point of time where recommendations are provided and the investment horizon largely affect the customer's investment performance.
Building on a proper selection of macroeconomic variables for constructing a Gross Domestic Product (GDP) forecasting multivariate model (Kazanas, 2017), this paper evaluates whether alternative Bayesian model specifications can provide greater forecasting accuracy compared to a standard Vector Error Correction model (VECM). To that end, two Bayesian Vector Autoregression models (BVARs) are estimated, a BVAR using Litterman’s prior (1979) and a BVAR with time-varying parameters (TVP-BVAR). Two forecasting evaluation exercises are then carried out, a 28-quarters ahead forecast and a recursive 4-quarters ahead forecast. The BVAR outperformed the other models in the first, whereas the TVP-VAR was the best-performing model in the second, highlighting the importance of having adjusting mechanisms, such as time-varying coefficients in a model.
Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI
Through collaboration between the Onassis Foundation, the Historical Archive of the National Bank of Greece, and the Vocational Senior High School of Kamatero, an innovative digital project was developed that is both trendy and geared towards youth. This project showcases how a concept aimed at emphasizing the historical significance of the Capital of Greece inspired students to merge the disciplines of Computer Science and History, resulting in the creation of a 3D game on a popular platform. Additionally, this project demonstrates how Project-based learning can be achieved through collaborative and inquiry-based learning, real-world connections, initiative, and the satisfaction of creating something new. The impetus for the cooperation was the Panhellenic Student Competition of the Onassis Foundation, "Hack the Map: Imaginary Worlds." This competition invited schools to promote the cultural heritage of Greece, especially cartographic exhibits/evidence of the old days, through students' digital projects. The Historical Archive of the National Bank of Greece, which is a significant resource for studying Modern Greek History through primary sources, reached out to the Vocational Senior High School of Kamatero, located in the western sector of Athens, to work on a project. The school has an IT department, among other disciplines. In close collaboration, they developed a scenario that is about the civil war that occurred in Athens during the Interregnum period (October 1862-October 1863) after the dethronement of Greece's first king, Otto I. The scenario highlights the bloody events that took place between political factions in the city. In these conflicts, the implication of "Kyriakos," a dangerous leader of robbers, is a paradoxical historical event that stimulated the 2nd-grade Informatics students' imagination. Therefore, they created a 3D digital game entitled "Thieves and Policemen in the newly established Greek city-state: Iouniana." This presentation intends to demonstrate how the students' team of the Vocational School of Kamatero rebuilt Athenian monuments related to Kyriakos' action in a 3D environment; how they reconstructed the cartography of the capital's center during the second half of the 19th century based on these monuments and how they utilized digital resources (maps, photos, and texts) and books proposed by NBG Historical Archives; how a single player, via Kyriakos' persona, has to accomplish missions-battles and match parts of Athens' map of that era; and finally, how students narrated a historical event in a game constructed in Roblox platform inviting other young people to involve history knowledge.
This research paper investigates housing price bubbles within the context of the residential real estate market in Greece, employing alternative analytical techniques and presenting novel econometric-based findings. The study concentrates on the temporal span from the first quarter of 1997 to the third quarter of 2022. Affordability and profitability indicators are employed to identify and evaluate episodes of either under- or overvaluation. Valuation is assessed by measuring the deviation of the price-to-rent ratio from its long-term average and trend, revealing an overvaluation of approximately 20% since the second quarter of 2019. Furthermore, the time-series properties of the dataset are subjected to rigorous econometric analysis, and specific housing-related hypotheses are empirically tested. Cointegration analysis yields varying implications for valuation depending on the chosen methodology and metric; nevertheless, the results collectively point to an overvaluation in terms of the price-to-income ratio. Moreover, among the four Right-Tailed Augmented Dickey-Fuller techniques employed, the Supremum Augmented Dickey-Fuller method identifies the presence of housing bubbles concerning the price-torent ratio. These bubbles are precisely dated using the Generalized Supremum Augmented Dickey-Fuller technique. The robustness of these findings is verified through the application of the Hodrick-Prescott Filter to real house prices. Remarkably, the most recent housing bubble episode, out of the four detected, persists until the final quarter of the sample period (2022Q3). This observation raises significant questions regarding its potential impact on the broader economy and necessitates a discussion on appropriate policy measures that should be considered.
