Articles
Permanent URI for this collection
Browse
Recent Submissions
- PublicationNew evidence on time-varying financial integration within Gulf Cooperation Council stock markets(2023)The aim of this study is to investigate the dynamics of regional financial integration among Gulf Cooperation Council (GCC) countries by pricing the local stock market return based on different risk premia related to the regional stock market and exchange market. Our approach is based on the international capital asset pricing model (ICAPM), which accounts for the degree of financial integration in the pricing of market risk premia. We also construct a regional currency basket, named Khaleeji, in order to obtain a reference currency in this area and to prospect the twin objective: a lesser peg to the US dollar and the emergence of regional monetary cooperation. Our main findings show that GCC stock markets are impacted by both regional and local financial shocks and crises. Analysis of the long-term dynamics highlights that the regional risk premium is not negligible for GCC countries, and better cooperation can enhance regional risk-sharing. The results also indicate that the degree of regional financial integration varies from country to country, leaning toward a partial integration level of GCC countries within their region. The increasing importance of regional risk premia and financial integration could encourage further financial cooperation among GCC countries, ultimately leading to better economic integration.
1 - PublicationForecasting CPI inflation under economic policy and geopolitical uncertainties(2024)Forecasting consumer price index (CPI) inflation is of paramount importance for both academics and policymakers at central banks. This study introduces the filtered ensemble wavelet neural network (FEWNet) to forecast CPI inflation, tested in BRIC countries. FEWNet decomposes inflation data into high- and low-frequency components using wavelet transforms, and incorporates additional economic factors, such as economic policy uncertainty and geopolitical risk, to enhance forecast accuracy. These wavelet-transformed series and filtered exogenous variables are input into downstream autoregressive neural networks, producing the final ensemble forecast. Theoretically, we demonstrate that FEWNet reduces empirical risk compared to fully connected autoregressive neural networks. Empirically, FEWNet outperforms other forecasting methods and effectively estimates prediction uncertainty, due to its ability to capture non-linearities and long-range dependencies through its adaptable architecture. Consequently, FEWNet emerges as a valuable tool for central banks to manage inflation and enhance monetary policy decisions.
5 - PublicationAuthigenic carbonate mineral formation in the Pagassitikos palaeolake during the latest Pleistocene, central Greece(2012)The Pagassitikos Gulf in Greece is a semi-enclosed bay with a maximum depth of 102 m. According to the present-day bathymetric configuration and the sea level during the latest Pleistocene, the gulf would have been isolated from the open sea, forming a palaeolake since ~32 cal. ka b. p. Sediment core B-4 was recovered from the deepest sector of the gulf and revealed evidence of a totally different depositional environment in the lowest part of the core: this contained light grey-coloured sediments, contrasting strongly with overlying olive grey muds. Multi-proxy analyses showed the predominance of carbonate minerals (aragonite, dolomite and calcite) and gypsum in the lowest part of the core. Carbonate mineral deposition can be attributed to autochthonous precipitation that took place in a saline palaeolake with high evaporation rates during the last glacial-early deglacial period; the lowest core sample to be AMS 14C dated provided an age of 19.53 cal. ka b. p. The palaeolake was presumably reconnected to the open sea at ~13.2 cal. ka b. p. during the last sea-level rise, marking the commencement of marine sedimentation characterised by the predominance of terrigenous aluminosilicates and fairly constant depositional conditions lasting up to the present day.
Scopus© Citations 8 11 - PublicationExploratory risk prediction of type II diabetes with isolation forests and novel biomarkers(2024)Type II diabetes mellitus (T2DM) is a rising global health burden due to its rapidly increasing prevalence worldwide, and can result in serious complications. Therefore, it is of utmost importance to identify individuals at risk as early as possible to avoid long-term T2DM complications. In this study, we developed an interpretable machine learning model leveraging baseline levels of biomarkers of oxidative stress (OS), inflammation, and mitochondrial dysfunction (MD) for identifying individuals at risk of developing T2DM. In particular, Isolation Forest (iForest) was applied as an anomaly detection algorithm to address class imbalance. iForest was trained on the control group data to detect cases of high risk for T2DM development as outliers. Two iForest models were trained and evaluated through ten-fold cross-validation, the first on traditional biomarkers (BMI, blood glucose levels (BGL) and triglycerides) alone and the second including the additional aforementioned biomarkers. The second model outperformed the first across all evaluation metrics, particularly for F1 score and recall, which were increased from 0.61 ± 0.05 to 0.81 ± 0.05 and 0.57 ± 0.06 to 0.81 ± 0.08, respectively. The feature importance scores identified a novel combination of biomarkers, including interleukin-10 (IL-10), 8-isoprostane, humanin (HN), and oxidized glutathione (GSSG), which were revealed to be more influential than the traditional biomarkers in the outcome prediction. These results reveal a promising method for simultaneously predicting and understanding the risk of T2DM development and suggest possible pharmacological intervention to address inflammation and OS early in disease progression.
10 3