Financial Anomalies Research Articles

Corporate Financial Risk Trend Prediction Using ARIMA-Based Machine Learning: A Semantic Literature Review

This research discusses the role of artificial intelligence (AI) technology in improving company financial risk predictions through the application of the Autoregressive Integrated Moving Average (ARIMA) model supported by machine learning. Using systematic literature analysis, this research explores how ARIMA, with the help of AI, can be applied in financial risk management to identify short-term and long-term trends, detect financial anomalies, and improve the quality of decision making. ARIMA models based on machine learning enable faster and more accurate identification of abnormal financial patterns, which is very important in helping companies respond to risks that have the potential to disrupt financial stability. Key findings show that the combination of ARIMA and AI not only makes it easier to analyze large and complex financial data, but also expands the potential of data-driven financial risk management by providing deeper insights. By integrating machine learning, ARIMA becomes more effective in handling dynamic and fluctuating financial data, so companies can anticipate risks more proactively. This study underscores the enormous potential of AI and ARIMA in helping companies build adaptive, high-precision risk prediction systems, offering new opportunities to strengthen financial resilience in an ever-changing business environment.

ANALYSIS OF FINANCIAL PERFORMANCE IN VARIOUS SECTORS: APPLICATION OF THE BENEISH M-SCORE MODEL IN CASABLANCA STOCK EXCHANGE MOROCCO

<p>This paper evaluates the financial performance of companies from different sectors on the Moroccan financial market, using the Beneish M-Score model. Initially developed to detect financial anomalies, the M-Score has evolved into a tool for assessing companies' overall financial performance and earnings quality. By analyzing financial indicators such as profitability, liquidity and operational efficiency, this study compares the financial dynamics of companies in sectors such as food, technology and transportation. The results highlight significant differences in performance, revealing both strengths and weaknesses in companies' financial management. The study also provides a comparison with industry standards, and offers recommendations for improving the assessment of financial performance using financial indicators and the M-Score.</p><p> </p><p><strong>JEL: </strong>G32, M41, L25</p><p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/soc/0778/a.php" alt="Hit counter" /></p>

Sentiment and Stock Characteristics: Comprehensive Study of Individual Investor Influence on Returns, Volatility, and Trading Volumes

Abstract Background Traditional asset pricing models face challenges from financial anomalies, prompting exploration through behavioural finance theory. This study analyses the nuanced relationship between individual investor sentiment and key stock market variables. Objectives To assess the impact of individual investor sentiment on stock returns, volatilities, and trading volumes using the American Association of Individual Investors (AAII) sentiment index. Methods/Approach Using regression models, we examine the relationship between individual investor sentiment and various stock characteristics across 480 components of the Standard & Poor's 500 index. Results We find a positive relationship between the AAII sentiment index and stock returns and a negative relationship with volatility and trading volume. Conclusions Our study contributes to understanding the intricate role of individual investor sentiment in financial markets.

Implementation of the ARIMA model for prediction of economic variables: evidence from the health sector in Brazil

In recent decades, quantitative models for forecasting economic crises have garnered significant interest from researchers, policymakers, and public and private institutions. Identifying the most appropriate models for predicting economic time series behaviors during crises is a pressing challenge. Effective techniques can be instrumental in forestalling financial irregularities, thus empowering institutions to deploy remedial actions and swiftly minimizing further economic setbacks. Contemporary literature introduces various forecasting models, such as the autoregressive integrated moving average (ARIMA) model. Recognized for its statistical alignment with numerous linear models, the ARIMA model has demonstrated its efficacy across various domains. This paper delves into applying the ARIMA model to predict five critical economic time series that substantially influenced Brazil’s public and private healthcare sectors throughout the economic crisis between 2000 and 2020. These time series encompassed the variables (i) the gross domestic product—GDP, (ii) the Extended National Consumer Price Index—IPCA, (iii) the unemployment rate, (iv) the total number of health plan beneficiaries, and (v) total number of individual health plan beneficiaries. Importantly, this study provides a comprehensive outline of the ARIMA implementation process, underscoring that precise forecasting is pivotal for managers aiming to curtail financial anomalies and avert resource shortages. The findings highlight the ARIMA model’s (1, 0, 2), (2, 2, 1), (0, 1, 2), (1, 1, 2), and (2, 2, 1) viability in accurately forecasting health-related time series, exceeding 95% accuracy for economic variables analyzed. These results have significant practical implications for healthcare managers and decision-makers. By offering accurate forecasts of critical economic metrics, such as the unemployment rate and the transition of beneficiaries between public and private health systems during economic downturns, this research provides valuable insights for strategic planning within the healthcare sector.

Post earnings announcement drift: A simple earnings surprise measure, the medium effect of investor attention and investing strategy

Drifting in the direction of earnings surprises for a prolonged period is a decades-puzzling financial anomaly, i.e., the “post-earnings-announcement drift” (PEAD). This paper provided a new simple but effective measure of earnings surprise called ORJ. Based on ORJ, not only is the medium effect of investors' attention on the relationship between earnings surprises and PEAD analyzed but also a tractable and profitable investing strategy is provided. Through comprehensive empirical analysis of the Chinese stock market, we found that i) both earnings surprises and investor attention can increase the degree of PEAD; ii) “good” (bad) earnings surprises strengthen (weaken) the degree of drift by accumulating (decreasing) investor attention; but it is asymmetric that the positive effects of “good” earnings surprises are stronger than the negative effects of “bad” earnings surprises on PEAD; and iii) the strategy obtains an average 6.78% return per quarter in excess of the market but only needs longing dozens of stocks; iv) Typical pricing factors such as the Fama-French three factors, illiquidity and company characteristics have little explanatory power to the returns of the strategy. This paper strongly demonstrates the importance of monitoring overnight returns of earnings announcements to digging the unexpected information and the potential profitability of PEAD in the Chinese market.

Enhancing audit accuracy: The role of AI in detecting financial anomalies and fraud

Enhancing audit accuracy: The role of AI in detecting financial anomalies and fraud

Firm-Level Investor Sentiment and Risk: Insight from Behavioral Finance

The aim of this study to analyses the investor sentiment, attentions and types of risk which are incurred after specific event like scam etc. This study used monthly dataset of prices from 2006 to 2022 due to availability of data. The event approach is used for data analysis with different data segregation like affected or unaffected datasets of firms. Firm-specific sentiment and attention increased slightly after the scam, indicating market interest and better firm perceptions. Political, noise trader, arbitrage, sovereign, and realised volatility increased during events. The perception of instability and uncertainty suggests scams increase market fears and risk aversion while attracting attention. A detailed comparison between scammed and unaffected firms showed stark differences. Financial scams lowered market confidence and firm stability, causing negative sentiment, lower attention, and higher risks across multiple dimensions. The differential impact suggests that scams' reputational and operational damage can cripple a firm's finances and investor perceptions. The study affects financial economics and market behaviour theory. The study shows how firm-specific sentiment and attention affect risk measures, explaining market dynamics' psychological and behavioural underpinnings. Financial anomalies like scams affect market outcomes due to investor sentiment and attention. Sentiment can force through risk perceptions, so integrated financial analysis models must account for behavioural and psychological factors. Financial scandals affect firm-specific and market-wide variables, according to event studies. With the insights, investors, regulators, and corporate managers can improve market and regulatory practices. This study examines how financial scams affect firm-specific and market-wide variables using theory and practice during and after event.

An improved BiGAN model for anomaly detection in finance

Financial systems play a pivotal role in shaping contemporary society, and the detection of financial anomalies holds immense significance in mitigating the adverse repercussions of market uncertainties on the global economy. In this context, this study presents an innovative LSTM-GANs model, specifically crafted to enhance the detection of anomalies in financial stock markets. The model introduces an "Anomaly Score" as a pivotal metric, which is computed through a combination of factors such as Reconstruction Loss, Latent Space Distance, and Discriminator Score. This composite score provides a quantitative assessment of the anomaly level within the financial data. By applying a predefined threshold to this Anomaly Score, the model efficiently identifies and flags anomalies. In a world where financial markets are increasingly complex and prone to unexpected events, the ability to detect and respond to anomalies swiftly is paramount. This novel LSTM-GANs model offers a promising approach to bolster the accuracy and effectiveness of financial anomaly detection, thereby contributing to the stability and resilience of global financial systems.

Blockchain-Data Mining Fusion for Financial Anomaly Detection: A Brief Review

Financial anomalies must be detected in order for financial institutions and regulatory bodies to manage risks and avoid fraudulent behavior. Financial anomaly detection is the practice of identifying unexpected or irregular financial transactions or patterns that may indicate fraudulent behavior or errors. It is crucial in today's digital era to prevent fraud, limit financial losses, and maintain secure financial systems. Various types of financial anomalies, such as credit card fraud, money laundering, financial statement fraud, and cryptocurrency fraud, pose significant risks to individuals and organizations. This review critically evaluates a selected research article on the use of blockchain technology in conjunction with data mining techniques to detect financial anomalies. The paper employs the case study method to demonstrate how well the suggested integrated system works in spotting financial anomalies. This review evaluates the article's methodology and conclusions and discusses its implications for practice. The report claims that merging data mining methods with blockchain technology can increase the precision and effectiveness of financial anomaly identification. This research advances knowledge about how block-chain technology and data mining techniques can be used to find financial abnormalities while also offering suggestions for further study and use.

Real-time Financial Anomaly Detection in SAP ERP Systems Using Ensemble Learning Surya Sai Ram Parimi

Real-time Financial Anomaly Detection in SAP ERP Systems Using Ensemble Learning Surya Sai Ram Parimi

Enterprise financial anomaly data detection method based on improved support vector machine

Enterprise financial anomaly data detection method based on improved support vector machine

Improving credit card fraud detection using machine learning and GAN technology

The motivation behind this study stems from identifying contemporary challenges associated with prosecuting electronic financial crimes. Highlights ongoing efforts to identify and address credit card fraud and fraud as there are many credit card fraud issues in the financial industry. Traditional methods are no longer able to keep up with modern methods of tracking the behavior of credit card users and detecting suspicious cases. Artificial intelligence technology offers promising solutions to quickly detect and prevent future fraud by credit card users. Datasets used to detect financial anomalies are affected by imbalances in financial transactions, and this study aims to address the imbalance of financial fraud datasets using adversarial algorithm techniques and compare them with the most commonly used methods in the scientific literature.The results showed that the function of the adversarial algorithm is consistent in several ways, including allowing researchers and interested parties to determine data growth rates, which helps bring the dataset closer to real-time data from financial markets and banks. This study proposes a hybrid machine learning model consisting of three machine learning algorithms: decision trees, logistic regression, and Naive Bayes algorithm, and calculates performance metrics such as accuracy, specificity, precision, and F1 score. Experimental results reveal varying degrees of accuracy in fraud detection. Model testing using the SMOTE method recorded an accuracy of 98.1% and an F-score of 98.3%. On the other hand, the oversampling and under sampling test methods showed similar performance, with the two methods recording an accuracy of 94.3 and 95.3 and an F-score of 94.7 and 95.1, respectively. Finally, the GAN method excelled, receiving a test score and accuracy of 99.9%, as well as exceptional precision, recall, and F1 score. As a result, we conclude that the GAN method is able to balance the data set, which in turn is reflected in the performance of the model in training and the accuracy of predictions when tested. Historical transaction analysis identifies behavioral patterns and adapts to evolving fraud techniques. This approach enhances transaction security and protects against potential financial losses due to fraud. This contribution allows financial institutions and companies to proactively combat fraudulent activities.

The Evaluation of Problems and Prospects of Admission Systems in GST (General, Science & Technology) Universities in Bangladesh

The study evaluates the Global Scholarship Test (GST) admission system in Bangladesh, focusing on its effectiveness in reducing costs, time of admission tests, and financial burden for students and guardians. The study used a structured questionnaire and closed-ended surveys to collect data from 400 respondents at Islamic University, Kushtia. The data reliability test was conducted from December 2023 to March 2024, with Cronbach’s alpha values of 0.80, 0.72, and 0.77. The study found that students and guardians agreed that the GST system reduced costs and time of admission tests, but faced issues such as time-consuming admission processes, coordination gaps, and financial difficulties. Reputable universities face financial anomalies, violation of statutes, rules, and ordinances, and ignored representatives of worthy resources. The GST authority should monitor management systems, reduce admission time, provide guidelines, and address long queuing systems. Automatic software could help address financial burdens for lower-scoring subjects.

Research on the Application of Machine Learning in Financial Anomaly Detection

Research on the Application of Machine Learning in Financial Anomaly Detection

Real-time Financial Anomaly Detection in SAP ERP Systems Using Ensemble Learning Surya Sai Ram Parimi

Real-time Financial Anomaly Detection in SAP ERP Systems Using Ensemble Learning Surya Sai Ram Parimi

How to measure earnings surprises: Based on revised market reaction.

We investigate the robustness of earnings surprise measures in the context of a revised market reaction. While existing literature suggests that financial anomalies may distort cumulative abnormal returns (CAR) during annual announcements, our research proves that a revised market reaction offers a more accurate reflection of investor reactions to earnings correction. Specifically, we introduce an innovative adjustment to CAR using stock price jumps, and prove that the fraction of misses on the same side (FOM) provides a superior measure of earnings surprises. Furthermore, we find that investor trading patterns align with FOM, and the post-earnings announcement drift (PEAD) strategy based on FOM outperforms that based on analysts' forecast error.

School Budget Development and Financial Accountability of Public Secondary Schools in Khwisero Sub County, Kenya

The Teachers Service Commission (TSC) raised concern about the misuse of funds in public secondary schools, warned principals in charge, and even indicated the interdiction of principals with financial anomalies. In Turkana South, the audit questioned the use of Kenya Shillings 29 million to buy three school buses, failing the school budget implementation plans. There were no logbooks for the said vehicles. According to audit reports on public secondary schools, financial statement anomalies have been reported in a number of schools in Khwisero Sub County. The school audit report indicated that some school managers had hidden fees that were not in line with the ones recommended by the government. The study objective was to assess the effect of school budget development on the financial accountability of public secondary schools in Khwisero Sub County. The study was guided by budget theory. The causal research design examined the cause-and-effect relationship between school budget development and financial accountability. A census survey was adopted in 25 public schools. Two respondents’ school bursar/accounts clerk and school principal were used for the study. This constituted 50 respondents. Data collection was aided by questionnaires and presented using tables. Descriptive and inferential analyses were conducted. The study found that school budget development had a beta value of 0.309 and a coefficient correlation of 0.890. The correlation R between the mean of school budget development and the mean of financial accountability had a beta term of β = 0.827, P = 0.000. This implies that statistically, budget development was significantly positive. The study recommends that public secondary schools should align budget-making with government policies and school demands. Furthermore, stakeholders such as parents and the school board should be involved in budget formulation.

Unraveling market mysteries: a comprehensive review of financial anomalies and puzzles

This comprehensive literature review consolidates various market anomalies and puzzles, providing an aggregated perspective to understand these complex dynamics that challenge the traditional Efficient Market Hypothesis. We examined numerous academic works to reveal insights into long-term return irregularities, earnings management influence on equity offerings, and information uncertainty’s impact on stock returns. The review delves into unique phenomena like persistent mutual fund performance, the day-of-the-week returns, the January effect, weather-induced mood shifts on the market, and the dynamics of multiple anomalies. International asset pricing and weekend anomalies were also discussed, with a particular focus on cryptocurrency efficiency. Incorporating behavioral finance perspectives, we explored social transmission bias, emotional finance, biased beliefs, investor optimism, sentiment, and global market inefficiencies. The influence of unique events and seasonal factors, such as the Super Bowl, daylight saving time, and the Halloween effect, were also analyzed. The review concludes by highlighting the evolving landscape of market anomalies, discussing ma- chine learning approaches to anomaly research, investor behavior challenges, and the disappearing anomalies in country and industry returns. It sets the groundwork for holistic comprehension of market anomalies, suggesting future research directions such as exploring new data sources, comprehensive theoretical modeling, and the role of technology, market regulations, and environmental changes on market anomalies.

The Impact of Investor Sentiment on Corporate Investment

With the development of the capital market and the real economy, enterprise investment is getting more and more attention; enterprise investment and the survival of the whole enterprise have a close link, with more and more phenomena presented in the market, the traditional finance in the "rational man" and "market effectiveness With more and more phenomena appearing in the market, the assumptions of "rational man" and "market effectiveness" in traditional finance are not enough to give these phenomena a reasonable explanation, and the emergence of behavioral finance relaxes the assumptions and makes the theory able to explain financial anomalies in the real market. China's capital market started late, and individual investors accounted for most factors in their investor decision-making that tend to irrational investment. This paper discusses the impact of investor sentiment changes on listed companies' investment from the perspective of behavioral finance and analyses the theoretical modeling and empirical modeling from two perspectives. Firstly, there are more individual investors in China's capital market, and it is more novel to study the investment angle of the capital market from the perspective of investor sentiment, so this study has significance to the market; secondly, it discusses the literature review of the relationship between investor sentiment and listed enterprises' investment by scholars in the past, and analyses the former's impact on the latter from theoretical modeling and puts forward hypotheses; after that, we use empirical methods to prove whether the hypotheses are valid or not; and finally analyses the results of the empirical research, the shortcomings of this paper's research and the constructive suggestions and future research space for the topics discussed in this paper.

Comparative Empirical Evidence of a Three-factor Model and a Five-factor Model Based on Anomalous Studies

The Fama-French three-factor model explains the magnitude of stock market returns by constructing three variable factors. The five-factor model adds two more factors to the three-factor model to provide a more accurate explanation of stock re-turns. These two factors have been widely used in the industry for decades since their inception. As China's securities industry has developed late, research on the stock industry has been more oriented towards empirical studies of the three-factor and five-factor models, and less research has been conducted on many financial anomalies that cannot be explained by traditional financial theory. This paper systematically describes the origins of factor anomaly research and five-factor anomaly research on the A-share market from 1997 to 2020, constructs new factors, compares and summarizes them with the old ones, and concludes that the three-factor anomaly model and five-factor anomaly model are not yet able to adequately explain A-share stocks and have larger errors when conducting empirical evidence; in contrast, the CPAM anomaly model can better conduct anomaly research, and the resulting In contrast, the CPAM is more suitable for the empirical study of anomalies and can pro-vide investors with more effective investment strategies and recommendations.