Deep Learning technologies have proven to be capable of making predictions in High-Frequency Trading, often reaching better results compared to other techniques traditionally used for this purpose. A Long Short-Term Memory (LSTM) architecture has been implemented because, despite noise, nonlinearity, nonstationarity and complexities in high-frequency data, this Recurrent Neural Network (RNN) deep learning technique allows for the discovery of interesting patterns, due to its peculiar features. Unlike traditional RNNs, which struggle to retain information over extended sequences, LSTM cells are able to selectively store and retrieve significant information from the past values. The goal of this paper is to study and implement a robust process for the fine-tuning of these nonlinear autoregressive models, analyze the results with the proper metrics, and evaluate the overall performance. A market case study based on an Italian stock has been analyzed to complement our discussion and we show how to improve the network performance using the technical indicator Williams %R as an exogenous variable related to volumes.

The impacts of the COVID-19 pandemic on finance remain inexhaustive, just as our knowledge of cryptocurrencies’ (henceforth “cryptos”) behavior is still emergent. We investigate the dynamic co-movements between cryptos and sustainable investment indices and how these relations evolve during the COVID-19 pandemic, and explore when and why cryptos co-move with sustainability-oriented investments. We especially focus on which crypto features and functionalities drive those links and how they change across COVID-19 regimes. Using daily data for the top 100 cryptos (from 1st January 2010 till 15th May 2024) and 14 sustainable investment indices covering environmental, social, and governance-related practices, sustainability screens, green technology, and renewable energy, we adopt a two-stage empirical design. In Stage 1 (detection), we use Granger causality and Dynamic Conditional Correlation-GARCH models to examine dynamic co-movements for each crypto-index pair. In Stage 2 (attribution), we use logistic regression to explain the incidence of co-movement using explicitly coded crypto characteristics and functions (consensus mechanism, smart contract capability, coin offering status, supply cap, stablecoin status, privacy status), estimated separately for pre-COVID, COVID and post-COVID periods. Three findings emerge. First, fewer than half of cryptos co-move with sustainability indices at any point. Second, among co-moving pairs, the share falls during COVID-19 and remains lower post-COVID than pre-COVID. Third, consensus mechanism and stablecoin status are robust, cross-regime drivers of co-movements, whereas other features are regime-dependent. Our contribution is to identify and quantify the feature-level drivers of co-movement between cryptos and sustainability indices at scale, across a broad asset universe and distinct market regimes, closing a scope gap in prior work focused on a few coins or composite indices. The results clarify when feature choices translate into stronger linkages with sustainability benchmarks, informing portfolio diversification, risk management, and regulatory assessment.

Manipulation in the stock market is a serious risk to the stability and integrity of financial markets. The daily volume of shares traded in the stock market is a natural process, as a result of which the number of shares traded on a daily basis is a naturally occurring phenomenon. Naturally occurring digits normally follow Benford’s law. The law states that the frequency of getting a smaller digit (1, 2, 3, …) as a leading digit of a number in a dataset is greater than that of a larger digit (9, 8, 7, …). To detect manipulation in the naturally occurring numbers, Benford’s law is widely used. It is a convenient method while dealing with a bulk quantity of data. In this paper, we used Benford’s law to study the probability of any manipulation in the daily volume of shares traded. The study sample has been collected from the financial service sector companies listed on the Bombay Stock Exchange of India. The study uses a total of 24,760 data points (2,476 data points in each company’s dataset) from April 2013 to March 2023 to analyze the daily volume of shares traded by the top 10 companies shorted by market capitalization. The study aims to assess the conformity of leading-digit distributions in the share’s daily trade volume to the logarithmic patterns predicted by Benford’s law. We applied the chi-square test to determine the statistical significance of the observed distribution by comparing it with the expected outcome based on Benford’s law. Out of 10 selected companies in this study, eight companies trade the volume of shares following Benford’s law, and the remaining two accept the null hypothesis. Deviations from the estimated outcome may indicate irregularities, anomalies, or intentional manipulations in the reported daily trade volume of shares.

The aim of this comprehensive review of the papers published on the Scopus database is to gain insights into the various indicators that determine the level of market efficiency within the global cryptocurrency markets. We have employed a series of bibliometric and content analyses on 3,224 papers published during 2014–2024. Findings indicate that the scholarly literature on cryptocurrency exhibits a varied range of perspectives, frequently encompassing multiple academic disciplines such as economics, finance, accounting, technology, and engineering. We present three significant findings. First, despite a growing list of recent studies supporting some efficiency, cryptocurrency assets frequently deviate from conventional norms of market efficiency. Herding, co-movement, sentiment, and overconfidence are the major contributors behind the inefficient cryptocurrency market. Second, the intricate nature of these assets and their lack of connection to fundamental economic value contribute to inconsistencies, instability, and ambiguity. Third, regulators are expected to intervene with prudent and globally collaborative regulations to optimize the potential of this market. In this discourse, we analyze the potential consequences derived from various frameworks and methods, with the aim of informing forthcoming scholarly investigations.

This study examines the impact of COVID-19 on the risk of the FinTech sector from a risk perspective. This study employs a multi-dimensional analysis approach and a rich data set that includes data from typical listed FinTech companies from 2016 to 2023. The research not only examines the overall risk level of the FinTech industry during the pandemic but also compares the risk changes in the FinTech industry with those in the traditional banking sector at different stages of the pandemic, revealing the unique risk characteristics of the financial technology industry when faced with the shocks of the pandemic. The results of the study indicate that COVID-19 has had a significant negative impact on risks in the FinTech sector, particularly in terms of risk of bankruptcy and risk of extreme losses. The findings of this study provide valuable information for regulators and investors in developing future crisis prevention and risk management strategies.

In the current regulatory environment, banks are required to quantify credit risk by means of default probabilities, loss rates conditional on default and expected exposures for a number of purposes: regulatory capital calculation, loan loss provisioning and stress testing. The nature of each credit risk parameter might be different for each application, e.g., forward looking default probabilities are needed for loan loss provisioning while regulatory capital is based on long-term averages. These different requirements for each purpose create a substantial burden especially for small and medium-sized banks. This paper describes a simple framework that allows the consistent calculation of credit risk parameters for all risk applications. It assumes that a bank is using a scorecard based on loan-level data where the data history might only span a couple of years. These data are combined with a macroeconomic model in a suitable way to derive risk parameters compliant with all regulatory requirements.

Nonperforming Assets (NPA) are the major problem for today’s Banking Industry, and it is being beheld that they are growing with time. So, through this study, the variables that lead to NPA are found. For the study, both bank-specific and macroeconomic variables are taken, to see whether the bank-specific too formulate an effect on NPA or they came out to be insignificant. The variables that lead to NPA are Management Efficiency, Asset Management, GDP, REER, NEER, Inflation, Unemployment and Real Interest Rate. The research for banks’ profitability to see if the same variables lead to NPA, moreover, influence profitability, but the result came out to be that there is only Asset Management, which impacts both. In the end, equity exploration on the four significant variables is conducted, to determine which bank has underperformed or overperformed on which variable.

This study makes an attempt to evaluate the impact of first and second waves of COVID-19 on the major global stock markets. Further, the study also analyzed the effect of COVID-19 on the sectoral indices of India during the first and second waves. In order to achieve the objective, the event study methodology has been used and abnormal returns are computed around the event dates. The findings of the study reveal that major stock markets in the world adversely affected during the first wave of COVID-19 and the highest abnormal loss was observed in Toronto Stock Exchange (7.55%) on the event date. The impact of second wave of COVID-19 was not as severe as first wave and highest abnormal loss (2.37%) was observed in Moscow Exchange of Russia. The Indian sectoral indices also showed high volatility during both the waves of COVID-19.

The purpose of the banking sector in the country is to provide banking services to all the people with a simple and easy manner with this view, PMJDY was introduced in 2014 to provide bank account to unbanked people free of cost and with simplification of KYC norms. All the incentives and monetary benefits to the targeted people will reach only through direct benefit transfer scheme which is linked with bank account and Aadhar. Banks also concentrate on urban and unbanked areas through single window banking and post office savings bank scheme. With this view, payment banks play a key role in banking penetration in the country. This paper made an attempt to discuss performance of payment banks with respect to financial performance.

Investment is the action of saving something at present for the probability of earning return in future. Women have broken various personal and social hindrances to earn and manage their money for the purpose of safeguarding their future. The factors that highly influence investment satisfaction include profitability, liquidity, tax implications, investment risk, investment stability, investment regulation, investment location, investment decision and investment service provider. The main purpose of the study is to analyze the factors that influence the investor’s satisfaction towards various investment avenues. It is very much challenging for the companies and various financial marketers, to understand the factors that influence the satisfaction of women investors. In order to earn return, the investors choose the suitable investment option based on their income and savings pattern. Factor analysis, linear multiple regression analysis and one-way analysis of variance have been used for data analysis. The result of the study states that various demographic factors and investment details influence the investment satisfaction of women investors.