A remark on some extensions of the mean-variance portfolio selection models

Quantitative risk management techniques should prove their efficacy when financially turbulent periods are about to occur. Along the common saying “who needs an umbrella on a sunny day?”, a theoretical model is really helpful when it carries the right suggestion at the proper time, that is when markets start behaving hecticly. The beginning of the third decade of the 21st century carried along a turmoil that severely affected worldwide economy and changed it, probably for good. A consequent and plausible research question could be this: which financial quantitative approaches can still be considered reliable? This article tries to partially answer this question by testing if the mean-variance selection model (Markowitz [16], [17]) and some of his refinements can provide some useful hints in terms of portfolio management.

Deep Learning for seasonality modelling in Inflation-Indexed Swap pricing

An Inflation-Indexed Swap (IIS) is a derivative in which, at every payment date, the counterparties swap an inflation rate with a fixed rate. For the calculation of the Inflation Leg cash flows it is necessary to build a mathematical model suitable for the Consumer Price Index (CPI) projection. For this purpose, quants typically start by using market quotes for the Zero-Coupon swaps in order to derive the future trend of the inflation index, together with a seasonality model for capturing the typical periodical effects. In this study, we propose a forecasting model for inflation seasonality based on a Long Short Term Memory (LSTM) network: a deep learning methodology particularly useful for forecasting purposes. The CPI predictions are conducted using a FinTech paradigm, but in respect of the traditional quantitative finance theory developed in this research field. The paper is structured according to the following sections: the first two parts illustrate the pricing methodologies for the most popular IIS: the Zero Coupon Inflation-Indexed Swap (ZCIIS) and the Year-on-Year Inflation-Indexed Swap (YYIIS); section 3 deals with the traditional standard method for the forecast of CPI values (trend + seasonality), while section 4 describes the LSTM architecture, and section 5 focuses on CPI projections, also called inflation bootstrap. Then section 6 describes a robust check, implementing a traditional SARIMA model in order to improve the interpretation of the LSTM outputs; finally, section 7 concludes with a real market case, where the two methodologies are used for computing the fair-value for a YYIIS and the model risk is quantified.

Covid-19 crisis and its impacts on the economic and financial sector

The World Bank data confirm that the recovery scenario will be different depending on the type of nation, the fundamentals of its economy, etc.. The Bank of Italy expects a growth of more than 4% for Italy at the end of 2021. The Italian banking system has shown great flexibility in dealing with the coronavirus emergency, taking a completely different form from the last in 2008 recession, when credit institutions were part of the problem. With their new social role, today in fact they are leading players. The health of the banking sector has also changed compared to 2008, with a stronger capital position, underlying the substantial resilience of the ecosystem and a more advanced expertise in NPL management. The role of the banks operating in Italy has been and will be to support firms, households and the growth of the economy with the sound and prudent distribution of credit, the offer of modern and efficient payment services thanks also to new technologies, business advice to companies for the development and internationalization. A clear evolution is opening up for banks in post-Covid towards digital business with a growing commitment in terms of investments in information technology.

Money laundering transaction detection with classification tree models

The detection of money laundering is a very important problem, especially in the financial sector. We propose a mathematical specification of the problem in terms of a classification tree model that ”automates” expert based manual decisions. We operationally validate the model on a concrete application that originates from a large Italian bank. The application of the model to the data shows a good predictive accuracy and, even more importantly, the reduction of false positives, with respect to the ”manual” expert based activity. From an interpretational viewpoint, while some drivers of suspicious laundering activity are in line with the daily business practices of the bank’s anti money laundering operations, some others are new discoveries.

Fundamental review of the trading book - Stato dell’arte sulle implementazioni dell’Internal Model Approach

In light of the finalization of the new regulatory framework for market with the adoption of the FRTB at EU level through the publication of CRR III, financial institutions are consolidating the implementations aimed to comply with the new regulatory requirements. The main purpose of this article is to analyze how banks are preparing for the go-live of IMA FRTB reporting – expected to be in January 2024 – focusing on the challenges that they are facing especially in terms of model transformations. In particular, an in-depth analysis will be carried out on the main methodological issues of the new regulatory context technicalities,in order to provide guidelines and market best practices on the Internal Model Approach (IMA) topics shared between Front Office, Risk Management as well as Control Structures.

Managing the Risks of Negative Interest Rates

The acceleration in the issuance of government debt since the global financial crisis has led central bankers to engineer interest rates that are historically low in nominal terms and consistently lower than inflation rates. Although the ostensible aim of this policy is to stimulate economic growth, maintaining negative real rates also goes a long way so that government debt is manageable and will decline in the long run, relative to the size of the economy. Financial institutions hold the great majority of government debt, and their books of retail and corporate loans are expanding briskly at a time when ultra-low interest rates make borrowing especially attractive. Rates paid on deposits are low, in advanced economies, even negative in the euro zone in nominal terms. That helps to offset the reduction in income that banks earn on their lending. Even so, the extreme and unique conditions resulting from persistent negative real interest rates mean that banks must take particular care to manage their interest-rate risk in the context of other risk types and the banks’ profit-and-loss analysis.

Fundamental review of the trading book: state of art on implementation of Standardised Approach

Following the publication of the regulatory framework for the Fundamental Review of the Trading Book (FRTB) by both the Basel Committee (BCBS) and the EU Regulator, the Financial Institutions have started the mandatory actions to comply with the new regulatory requirements. This article aims to provide an overview of the key challenges that banks have had to face in recent years, with a particular focus on the most significant methodological key points and the main impacts on business from the technicalities of the new regulatory framework, in order to provide guidelines and best practices on Standardized Approach (SA) topics shared between Risk Management and Front Office

Fintech & Risks. A Bibliometric Analysis

Our study highlights a literature map on Fintech and the risks associated with this technological innovation in the financial sector. Considering all the studies published from 2014 to 2021 in "Scopus", we resort to econometric techniques to create our map. Our results show the recent attention of academics and researchers, mainly belonging to the technological and IT areas, towards Fintech. In particular, the studies focus on the issue of emerging technologies applied to investment and credit processes linked to the assessment of customer insolvency risk. For this reason, the existing analyzes adopt a mainly technical approach with very limited attention to strategic, organizational and managerial aspects typical of financial intermediation. Future studies could investigate the issue of Fintech behavior and relations with incumbent banks, as well as the risks that the applications of emerging digital technologies have on the sound and prudent management of these operators. In addition, further analysis can capture the risks of Fintech for clients, taking into account financial education. These are important aspects for the growth of Fintechs themselves, for the sustainability of the incumbent banks, with which they increasingly collaborate, and obviously for the banking supervisory authorities, attentive to the stability, efficiency and competitiveness of the financial sector as a whole.

Why segmentation matters: a Machine Learning approach for predicting loan defaults in the Peer-to-Peer (P2P) Financial Ecosystem

Peer-to-Peer (P2P) lending is an online lending process allowing individuals to obtain or concede loans without the interference of traditional financial intermediaries. It has grown quickly the last years, with some platforms reaching billions of dollars of loans in principal in a short amount of time. Since each loan is associated with the probability of loss due to a borrower's failure, this paper addresses the borrower's default prediction problem in the P2P financial ecosystem. The main assumption, which makes this study different from the available literature, is that borrowers sharing the same homeownership status display similar risk profile, thus a model per segment should be developed. We estimate the Probability of Default (PD) of a borrower by using Logistic Regression (LR) coupled with Weight of Evidence encoding. The features set is identified via the Sequential Feature Selection (SFS). We compare the forward against the backward SFS, in terms of the Area Under the Curve (AUC), and we choose the one that maximizes this statistic. Finally, we compare the results of the chosen LR approach against two other popular Machine Learning (ML) techniques: the k Nearest Neighbors (k-NN) and the Random Forest (RF).

Reputational Risk for financial institutions: a proposal of quantitative approach

The reputation of an institution refers to its public image in terms of competence, integrity and trustworthiness, which results from the awareness of its stakeholders. The related risk, i.e. “Reputational Risk”, is defined as the current or prospective risk of a decline in profits or capital resulting from a negative perception of the financial institution image by clients, counterparties, shareholders, investors or supervisory authorities. In this scenario, the reputation and the assessment of the associated risk component represent a decisive factor for ensuring long-lasting profitability. In recent years, the importance of managing and monitoring Reputational Risk is growing in importance with supervisory authorities, but nevertheless, there are no specific guidelines yet that the institutions can follow. The lack of a precise orientation means that the risk component is still considered discretionary, subjective and highly prone to interpretation. Considering that in the economic literature there is not a universally accepted approach, the aim of the paper is to provide a quantitative and objective methodology, a Quantitative Model, to assess the Reputational Risk in order to overcome the limits of a qualitative approach, by using exclusively numerical and objective analysis drivers, and to meet the increasing attention of the supervisory authorities on the issue. The Quantitative Model structure allows firms to study and to monitor the phenomenon from a managerial point of view. This approach provides financial institutions, in particular the Risk Management Department, a model to evaluate the reputational risk arising from economic magnitudes that characterise the business model of the financial institution. This means that the quantitative Model enables financial institutions to steering possible negative situations and promptly intervening with any corrective measures or actions deemed appropriate.