Search

This paper analyses the recent evolution of the electricity price of one of the East-European countries' Balancing Markets (BM) - Romania, aiming to understand the prices trend and predict them in the current economic and geopolitical context. This is especially important as the electricity producers have to allocate their output between wholesale electricity market, ancillary services markets and BM targeting to maximize value and achieve a sustainable economic development. Therefore, in this paper, we propose an AI-powered electricity price forecast using several types of standout Machine Learning (ML) algorithms such as classifiers and regressors to predict the electricity price on BM. This approach, consisting of two steps, identifies the imbalance sign and significantly enhances the performance of the price forecast. The proposed method offers valuable insights into the market participants' trading opportunities using two prediction solutions. The first prediction solution consists of averaging the results of five ensemble ML algorithms. The second one consists in weighting the results of the five forecasting ML algorithms using either a linear regression or a decision tree algorithm. Thus, we propose to combine supervised and unsupervised ML algorithms and find the fundamentals for creating optimal bidding strategies for electricity market players. [ABSTRACT FROM AUTHOR]

According to the trading rules and financial data structure of the stock index futures market, and considering the impact of major emergencies, we intend to build a quantitative investment decision-making model based on machine learning. We first adopt the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) signal decomposition technology to separate the short-term noise, cycle transformation and long-term trend from the original series, and use the CSI 500 Baidu index series to reflect the investors' attention, which provides data support for establishing a more effective forecasting model. Then, the CEEMDAN-BP neural network model is designed based on the obtained effective information of low-frequency trend series, investor attention index and CSI 500 stock index futures market transaction data. Finally, an Attention-based Dual Thrust quantitative trading strategy is proposed and optimized. The optimized Attention-based Dual Thrust strategy solves the core problem of breakout interval determination, effectively avoids the risk of subjective selection, and can meet investors' different risk preferences. The quantitative investment decision-making model based on CEEMDAN-BP neural network utilizes the advantages of different algorithms, avoids some defects of a single algorithm, and can make corresponding adjustments according to changes in investors' attention and the occurrence of emergencies. The results show that considering investor attention can not only improve the predictive ability of the model, but also reduce the cognitive bias of the market, effectively control risks and obtain higher returns. [ABSTRACT FROM AUTHOR]

Financial systemic risk is an important issue in economics and financial systems. Trying to detect and respond to systemic risk with growing amounts of data produced in financial markets and systems, a lot of researchers have increasingly employed machine learning methods. Machine learning methods study the mechanisms of outbreak and contagion of systemic risk in the financial network and improve the current regulation of the financial market and industry. In this paper, we survey existing researches and methodologies on assessment and measurement of financial systemic risk combined with machine learning technologies, including big data analysis, network analysis and sentiment analysis, etc. In addition, we identify future challenges, and suggest further research topics. The main purpose of this paper is to introduce current researches on financial systemic risk with machine learning methods and to propose directions for future work. [ABSTRACT FROM AUTHOR]

Trade-based Money Laundering, a new form of money laundering using international trade as a signboard, always appears along with speculative capital movement which has been accepted as the most concerned and consensus incentive giving rise to the collapse of the financial market. Unfortunately, preventing money laundering is very difficult since money laundering always has a plausible trade characterization. To reach this goal, supervision for regulator and financial institutions aims to effectively monitor micro entities' behavior in financial markets. The main purpose of this paper is to establish a monitoring method including accurate recognition and classified supervision for Trade-based Money Laundering by means of knowledge-driven multi-class classifi- cation algorithms associated with macro and micro prudential regulation, such that the model can forecast the predicted class from the concerned management areas. Based on empirical data from China, we demonstrate the application and explain how the monitor method can help to improve management efficiency in the financial market. [ABSTRACT FROM AUTHOR]

Support vector machines (SVMs), with their roots in Statistical Learning Theory (SLT) and optimization methods, have become powerful tools for problem solution in machine learning. SVMs reduce most machine learning problems to optimization problems and optimization lies at the heart of SVMs. Lots of SVM algorithms involve solving not only convex problems, such as linear programming, quadratic programming, second order cone programming, semi-definite programming, but also non-convex and more general optimization problems, such as integer programming, semi-infinite programming, bi-level programming and so on. The purpose of this paper is to understand SVM from the optimization point of view, review several representative optimization models in SVMs, their applications in economics, in order to promote the research interests in both optimization-based SVMs theory and economics applications. This paper starts with summarizing and explaining the nature of SVMs. It then proceeds to discuss optimization models for SVM following three major themes. First, least squares SVM, twin SVM, AUC Maximizing SVM, and fuzzy SVM are discussed for standard problems. Second, support vector ordinal machine, semisupervised SVM, Universum SVM, robust SVM, knowledge based SVM and multi-instance SVM are then presented for nonstandard problems. Third, we explore other important issues such as lp-norm SVM for feature selection, LOOSVM based on minimizing LOO error bound, probabilistic outputs for SVM, and rule extraction from SVM. At last, several applications of SVMs to financial forecasting, bankruptcy prediction, credit risk analysis are introduced. [ABSTRACT FROM AUTHOR]

This paper is aimed at examining the role of annual reports’ sentiment in forecasting financial performance. The sentiment (tone, opinion) is assessed using several categorization schemes in order to explore various aspects of language used in the annual reports of U.S. companies. Further, we employ machine learning methods and neural networks to predict financial performance expressed in terms of theZ-score bankruptcy model. Eleven categories of sentiment (ranging from negative and positive to active and common) are used as the inputs of the prediction models. Support vector machines provide the highest forecasting accuracy. This evidence suggests that there exist non-linear relationships between the sentiment and financial performance. The results indicate that the sentiment information is an important forecasting determinant of financial performance and, thus, can be used to support decision-making process of corporate stakeholders. [ABSTRACT FROM AUTHOR]

Banks and financial institutions rely on loan default prediction models in credit risk management. An important yet challenging task in developing and applying default classification models is model evaluation and selection. This study proposes an evaluation approach for bank loan default classification models based on multiple criteria decision making (MCDM) methods. A large real-life Chinese bank loan dataset is used to validate the proposed approach. Specifically, a set of performance metrics is utilized to measure a selection of statistical and machine-learning default models. The technique for order preference by similarity to ideal solution (TOPSIS), a MCDM method, takes the performances of default classification models on multiple performance metrics as inputs to generate a ranking of default risk models. In addition, feature selection and sampling techniques are applied to the data pre-processing step to handle high dimensionality and class unbalancedness of bank loan default data. The results show thatK-Nearest Neighbor algorithm has a good potential in bank loan default prediction. [ABSTRACT FROM AUTHOR]

Credit scoring, which is typically transformed into a classification problem, is a powerful tool to manage credit risk since it forecasts the probability of default (PD) of a loan application. However, there is a growing trend of integrating survival analysis into credit scoring to provide a dynamic prediction on PD over time and a clear explanation on censoring. A novel dynamic credit scoring model (i.e., SurvXGBoost) is proposed based on survival gradient boosting decision tree (GBDT) approach. Our proposal, which combines survival analysis and GBDT approach, is expected to enhance predictability relative to statistical survival models. The proposed method is compared with several common benchmark models on a real-world consumer loan dataset. The results of out-of-sample and out-of-time validation indicate that SurvXGBoost outperform the benchmarks in terms of predictability and misclassification cost. The incorporation of macroeconomic variables can further enhance performance of survival models. The proposed SurvXGBoost meanwhile maintains some interpretability since it provides information on feature importance. [ABSTRACT FROM AUTHOR]