Semi-Supervised Clustering for Financial Risk Analysis

Many methods have been developed for financial risk analysis. In general, the conventional unsupervised approaches lack sufficient accuracy and semantics for the clustering, and the supervised approaches rely on large amount of training data for the classification. This paper explores the semi-supervised scheme for the financial data prediction, in which accurate predictions are expected with a small amount of labeled data. Due to lack of sufficient distinguishability in financial data, it is hard for the existing semi-supervised approaches to obtain satisfactory results. In order to improve the performance, we first convert the input labeled clues to the global prior probability, and propagate the’soft’ prior probability to learn the posterior probability instead of directly propagating the’hard’ labeled data. A label diffusion model is then constructed to adaptively fuse the information at feature space and label space, which makes the structures of data affinity and labeling more consistent. Experiments on two public real financial datasets validate the effectiveness of the proposed method.

Optimization of a 660 MWe Supercritical Power Plant Performance—A Case of Industry 4.0 in the Data-Driven Operational Management Part 1. Thermal Efficiency

This paper presents a comprehensive step-wise methodology for implementing industry 4.0 in a functional coal power plant. The overall efficiency of a 660 MWe supercritical coal-fired plant using real operational data is considered in the study. Conventional and advanced AI-based techniques are used to present comprehensive data visualization. Monte-Carlo experimentation on artificial neural network (ANN) and least square support vector machine (LSSVM) process models and interval adjoint significance analysis (IASA) are performed to eliminate insignificant control variables. Effective and validated ANN and LSSVM process models are developed and comprehensively compared. The ANN process model proved to be significantly more effective; especially, in terms of the capacity to be deployed as a robust and reliable AI model for industrial data analysis and decision making. A detailed investigation of efficient power generation is presented under 50%, 75%, and 100% power plant unit load. Up to 7.20%, 6.85%, and 8.60% savings in heat input values are identified at 50%, 75%, and 100% unit load, respectively, without compromising the power plant’s overall thermal efficiency.

A Labeling Method for Financial Time Series Prediction Based on Trends

Time series prediction has been widely applied to the finance industry in applications such as stock market price and commodity price forecasting. Machine learning methods have been widely used in financial time series prediction in recent years. How to label financial time series data to determine the prediction accuracy of machine learning models and subsequently determine final investment returns is a hot topic. Existing labeling methods of financial time series mainly label data by comparing the current data with those of a short time period in the future. However, financial time series data are typically non-linear with obvious short-term randomness. Therefore, these labeling methods have not captured the continuous trend features of financial time series data, leading to a difference between their labeling results and real market trends. In this paper, a new labeling method called "continuous trend labeling" is proposed to address the above problem. In the feature preprocessing stage, this paper proposed a new method that can avoid the problem of look-ahead bias in traditional data standardization or normalization processes. Then, a detailed logical explanation was given, the definition of continuous trend labeling was proposed and also an automatic labeling algorithm was given to extract the continuous trend features of financial time series data. Experiments on the Shanghai Composite Index and Shenzhen Component Index and some stocks of China showed that our labeling method is a much better state-of-the-art labeling method in terms of classification accuracy and some other classification evaluation metrics. The results of the paper also proved that deep learning models such as LSTM and GRU are more suitable for dealing with the prediction of financial time series data.

An Intelligent and Dynamic Decision Support System for Nonlinear Environments

Nonlinear time series systems are high dimensional and chaotic in nature. Since, the design of a dynamic and efficient decision making system is a challenging task, a Support Vector Machine (SVM) based model is proposed to predict the future event of a nonlinear time series environment. This model is a non-parametric model that uses the inherent structure of the data for forecasting. The Hybrid Dimensionality Reduction (HDR) and Extended Hybrid Dimensionality Reduction (EHDR) techniques are proposed to represent the time series data and to reduce the dimensionality and control noise besides subsequencing the time series data. The proposed SVM based model using EHDR is compared with the models using Symbolic Aggregate approXimation (SAX), HDR, SVM using Kernel Principal Component Analysis(KPCA) and SVM using varying tube size values for historical data on different financial instruments. The experimental results have proved that the prediction accuracy of the proposed model is better compared with other models taken for the experimentation.

Modeling mercury speciation in combustion flue gases using support vector machine: prediction and evaluation

Mercury emission from coal combustion has become a global environmental problem. In order to accurately reveal the complexly nonlinear relationships between mercury emissions characteristics in flue gas and coal properties as well as operating conditions, an alternative model using support vector machine (SVM) based on dynamically optimized search technique with cross-validation, is proposed to simulate the mercury speciation (elemental, oxidized and particulate) and concentration in flue gases from coal combustion, then the configured SVM model is trained and tested by simulation results. According to predicted accuracy of indicating generalization capability, the model performance is compared and evaluated with the conventional multiple nonlinear regression (MNR) models and the artificial neural network (ANN) models. As a result, it is found that, the SVM provides better prediction performances with the mean squared error of 0.0095 and the correlation coefficient of 0.9164 for testing sample. Moreover, based on the SVM model, the correlativity between coal properties as well as operating condition and mercury chemical form is also analyzed in order to deeply understand mercury emissions characteristics. The result demonstrates that SVM can offer an alternative and powerful approach to model mercury speciation in coal combustion flue gases.