Predicting stock market price is considered as a challenging task of financial time series analysis, which is of great interest to stock investors, stock traders and applied researchers. Many machine learning techniques have been used in this area to predict the stock market price, including regression algorithms which can be useful tools to provide good performance of financial time series prediction. Support Vector Regression is one of the most powerful algorithms in machine learning. There have been countless successes in utilizing SVR algorithm for stock market prediction. In this paper, we propose a novel hybrid approach based on machine learning and filtering techniques. Our proposed approach combines Support Vector Regression and Hodrick–Prescott filter in order to optimize the prediction of stock price. To assess the performance of this proposed approach, we have conducted several experiments using real world datasets. The principle objective of this paper is to demonstrate the improvement in predictive performance of stock market and verify the works of our proposed model in comparison with other optimized models. The experimental results confirm that the proposed algorithm constitutes a powerful model for predicting stock market prices.

Stock market prediction is regarded as a challenging task of financial time-series prediction. There have been many studies using machine learning techniques in this area. A large number of successful applications have shown that regression algorithms can be very useful tools for time-series modelling and forecasting. In this paper we run a comparative study of three of these algorithms: Multiple Linear Regression, Support Vector Regression and Decision Tree Regression in order to determine their performances in term of implementing financial time series forecasts. To assess the performance of these algorithms, we have conducted experiments using L'Oréal financial dataset. The results exhibit that support vector regression produced the best forecasts.

Predicting stock prices is an important task of financial time series forecasting, which is of great interest to stock investors, stock traders and applied researchers. Many machine learning techniques have been used in recent times to predict the stock price, including regression algorithms which can be useful tools to provide good accuracy of financial time series forecasting. In this paper, we propose a novel hybrid approach which combines Support Vector Regression and Hodrick-Prescott filter in order to optimize the prediction of stock price. To assess the performance of this proposed approach, we have conducted several experiments using Maroc Telecom (IAM) financial time series. It is daily data collected during the period between 2004 and 2016. The experimental results confirm that the proposed model is more powerful in term of predicting stock prices.

Purpose: Most local governance assessment tools are entirely or partially based on stakeholders’ surveys, focus groups and benchmarks of different local governments in the world. These tools remain a subjective way of local governance evaluation. To measure the performance of local good-governance using an unbiased assessment technique, the authors have developed a framework to help automate the design process of a data warehouse (DW), which provides local and central decision-makers with factual, measurable and accurate local government data to help assess the performance of local government. The purpose of this paper is to propose the extraction of the DW schema based on a mixed approach that adopts both i* framework for requirements-based representation and domain ontologies for data source representation, to extract the multi-dimensional (MD) elements. The data was collected from various sources and information systems (ISs) deployed in different municipalities. Design/methodology/approach: The authors present a framework for the design and implementation of a DW for local good-governance assessment. The extraction of facts and dimensions of the DW’s MD schema is done using a hybrid approach, where the extraction of requirement-based DW schema and source-based DW schema are done in parallel followed by the reconciliation of the obtained schemas to obtain the good-governance assessment DW final design. Findings: The authors developed a novel framework to design and implement a DW for local good-governance assessment. The framework enables the extraction of the DW MD schema by using domain ontologies to help capture semantic artifacts and minimize misconceptions and misunderstandings between different stakeholders. The introduction and use of domain ontologies during the design process serves the generalization and automation purpose of the framework. Research limitations/implications: The presently conducted research faced two main limitations as follows: the first is the full automation of the design process of the DW and the second, and most important, is access to local government data as it remains limited because of the lack of digitally stored data in municipalities, especially in developing countries in addition to the difficulty of accessing the data because of regulatory aspects and bureaucracy. Practical implications: The local government environment is among the public administrations most subject to change-adverse cultures and where the authors can face high levels of resistance and significant difficulties during the implementation of decision support systems, despite the commitment/engagement of decision-makers. Access to data sources stored by different ISs might be challenging. While approaching the municipalities for data access, it was done in the framework of a research project within one of the most notorious universities in the country, which gave more credibility and trust to the research team. There is also a need for further testing of the framework to reveal its scalability and performance characteristics. Originality/value: Compared to other local government assessment ad hoc tools that are partially or entirely based on subjectively collected data, the framework provides a basis for automated design of a comprehensive local government DW using e-government domain ontologies for data source representation coupled with the goal, rationale and business process diagrams for user requirements representations, thus enabling the extraction of the final DW MD schema.

Forecasting is an important activity in economics, finance, marketing and various other domains like environmental and social sciences. There are several methods for making forecasts, but they all fall into two categories: causal methods and time series methods. In many cases, predictive algorithms implementing time series are good candidates for forecasting. In this paper we run a comparative study of three of these algorithms: Linear Regression, Support Vector Machines and Multilayer Perceptron in order to determine their performances in term of implementing times series for predictive systems. To assess the performance of these algorithms, we have conducted experiments over four representative datasets. The results exhibit that linear regression produced the best forecasts. The other two algorithms show a good behavior as well.