Fig 10 - uploaded by Uduak A. Umoh
Content may be subject to copyright.
Source publication
ABSTRACT
The operations of the prediction of stock price are complex and risky due to fluctuation in the stock market because of the vagueness, incompleteness, and uncertainty of the information used. However, it is therefore as a matter of necessity to seek to foresee stock prices because traders need to know when to invest in order to get the max...
Similar publications
The purpose of this research is to analyze the response of Indonesian Capital Market to increase in fuel price as announced by the Government on June 22 nd , 2013. This study uses abnormal returns and trading volume activity as the indicators to observe investors' responses in the capital market. Event study is used in order to examine investors' r...
We investigate the synchronicity of extreme stock returns by using the individual stock trading data from WIND database during a time span from May 1st 2014 to Dec 31th 2016 and find that there is an asymmetrical pattern of stock prices co-movement with respect to extreme market conditions, namely, the individual stock prices tend to fall down at t...
On any Stock Exchange, share prices rise and fall depending, largely, on market forces. These market forces are determined by information dissemination to the market. There have been periods when the Zimbabwe Stock Exchange (ZSE) move drastically up and down, but without any apparent economic news or stimulus, therefore it has become hard to predic...
Volatility is a statistical measure of stock price fluctuation. This study aims to investigate the effect of trading volume, firm size, inflation, and exchange rate on stock price volatility of the companies included in the Jakarta Islamic Index (JII) from 2014 to 2018. By using a purposive sampling technique, the research sample is sixteen compani...
The Random Walk Hypothesis (RWH) states that stock prices move randomly in the stock market without following any regular or particular pattern and as such historical information contained in the past prices of stocks cannot be used to predict current or future stock prices. Hence, stock prices are unpredictable and that investors cannot usurp any...
Citations
... According to A. A. Udosen et al., [6], the notable successes recorded with voting ensemble learning models, an artificial intelligence (AI) algorithm, highlight their potential for exploitation. A. A. Abiona et al., [7] and U. A. Umoh et al., [8] argued that AI improves decision-making and optimizes output. Additionally, T. Deep Singh et al., [9] stated that machine learning enables computers to learn automatically and enhances their performance without explicit programming. ...
The rapid industrialization and technological advancements of recent decades have significantly improved various facets of human life but have also intensified air pollution through the emission of harmful gases. Accurate detection of these pollutants, including Carbon Monoxide (CO), Ammonia (NH₃), and Sulfur Dioxide (SO₂), is critical for mitigating environmental and health hazards. Traditional sensor technologies often fail due to calibration issues and susceptibility to extreme temperatures, underscoring the need for advanced monitoring solutions. This study investigates the integration of artificial intelligence (AI), particularly ensemble machine learning models, to address these challenges. Leveraging the Gas Sensor Array Drift Dataset, a Voting Ensemble Learning Model (VELM) was developed and benchmarked against individual machine learning classifiers such as Random Forest, Support Vector Machine, and Logistic Regression. The VELM demonstrated superior performance, achieving a classification accuracy of 99.46%, surpassing conventional methods while maintaining low variance. Despite marginal accuracy differences with Random Forest, VELM's majority voting approach consistently ensured robust performance. The findings highlight the transformative potential of ensemble learning in environmental monitoring and provide a foundation for future research. Recommendations include exploring deep learning enhancements and deploying the model in real-world settings to refine its applicability for detecting a broader range of harmful gases, thereby advancing public safety and environmental sustainability.
... Logika Fuzzy adalah cabang dari sistem kecerdasan buatan (Artificial Intelegent). Lotfi A. Zadeh mendefinisikan logika fuzzy sebagai suatu prinsip matematika berdasarkan derajat keanggotaan dari logika biner klasik yang digunakan untuk representasi pengetahuan (Umoh, et al, 2014). Logika Fuzzy Banyak dikembangkan karena mempunyai keunggulan dalam penyelesaian masalah yang mengandung ketidakpastian, ketidaktepatan dan kebenaran parsial. ...
Logika fuzzy merupakan cabang dari kecerdasan buatan yang mempunyai keunggulan dalam menyelesaikan masalah yang mengandung ketidakpastian, ketidaktepatan dan kebenaran parsial. Penilaian kualitas Singkong yang digunakan untuk bahan kerupuk Sanjai mengandung ketidakpastian. Tidak ada yang bisa dengan mudah mudah mengetahui kualitas Singkong tersebut. Ada tiga kriteria yang digunakan untuk menentukan kualitas Singkong yang digunakan untuk bahan baku kerupuk Sanjai yaitu ukuran Singkong, umur Singkong dan lama Singkong disimpan sebelum diolah. Penilaian kualitas Singkong menggunakan logika fuzzy metode Sugeno. Penerapan logika fuzzy metode Sugeno mempunyai tiga tahapan yaitu fuzzifikasi, inference dan defuzzifikasi. Pengujian metode Sugeno ini menggunakan software Matlab 6.1. Diambil 15 Singkong yang digunakan untuk sampel dan kemudian diuji dengan Matlab dan dihasilkan 15 Singkong tersebut mempunyai kualitas baik. Keyword: Logika Fuzzy, Metode Sugeno, Kualitas Singkong
... Where _(A ) (x) is the membership function for the fuzzy set, the membership function maps each element from X to the degree of membership that lies in the range [0,1] [20], [21]. The fuzzy set has two attributes [22], namely: linguistic and numerical. ...
Red chili is Indonesia's leading commodity. Red chili is a raw material for various food products, cosmetics, pharmaceuticals and others. Fluctuations in the availability of red chili commodity supply affect the price of red chili commodity products. Pricing can occur because of supply and demand. Uncertain conditions also influence pricing due to fluctuations in raw material prices, ultimately affecting the price of carrageenan products. This condition makes price determination very difficult. Therefore, this study aims to analyze and design a pricing mechanism and determine the optimal margin in the red chili commodity marketing system. This study uses a systems analysis and design approach. Input-process-output (IPO) diagrams describe system requirements. Industrial business processes are described by the Business Process Model and Notation (BPMN) ver. 16.0. Meanwhile, to determine the optimal margin, Sugeno's fuzzy inference system approach is used by simulating the model in 3 margin scenarios: pessimistic, moderate, and optimistic. The simulation results were tested using the MAPE test, in which the results were compared between fuzzy price results and markup prices using markup values of 20%, 25%, and 30%. The analysis results show that the price is determined by demand and supply. The price obtained from the formulation of the Sugeno fuzzy model shows an optimal margin of Rp. 16,600.
... Wireless ad networks represent live streaming systems that are fully distributed without infrastructure [7]. Significant disruption occurs when multiple transfers occur with links to the same or different codes, thus leading to additional problems and issues such as delay, jitter, limited bandwidth, packet loss (packet loss), etc., which also affects service level (QoS) [8].Over the past few years, wireless networks have attracted a lot of research across the network and social functioning [9]. Recently, multimedia programs on ad hoc wireless have become increasingly common, but even largely the effects of delays and packet loss challenges [10]. ...
The rate at which hackers have devised means of increasing threats is becoming unbearable. Classified information is no longer confidential in financial institutions and academic environments. Government agencies and election organizers are no exception in these nefarious activities. The resultant effect is a decline in the number of subscribers that patronize the affected telecommunication companies. The threats could be minimized or prevented by introducing a smart means of checking to eliminate the threats to improve the security management in the higher institution or multimedia environment using intelligent agents. The methodology used to understand the nature of threats and types of threats observed in multimedia could be outlined as follows: Designing a smart rule base that will detect and reduce threats in multimedia, training Artificial Neural Network (ANN) in the multimedia rule base to increase the efficiency of the rules. The next stage is to design a SIMULINK model for improving security management in the higher institution using Artificial Intelligence (Neuro-fuzzy software). The results obtained are highest without Neuro-Fuzzy Controller with percentage threat level recorded as is 83% while that when Neuro-fuzzy is incorporated in the system is 81.18%. This clearly shows that there is an obvious percentage reduction in the number of threats when Neuro-fuzzy is incorporated into the system. The positive performance index was 1.82%.
KEYWORDS Improving, Cyber-attack, Hackers, Artificial Intelligence, Tertiary Institutions
... Wireless ad networks represent live streaming systems that are fully distributed without infrastructure [7]. Significant disruption occurs when multiple transfers occur with links to the same or different codes, thus leading to additional problems and issues such as delay, jitter, limited bandwidth, packet loss (packet loss), etc., which also affects service level (QoS) [8].Over the past few years, wireless networks have attracted a lot of research across the network and social functioning [9]. Recently, multimedia programs on ad hoc wireless have become increasingly common, but even largely the effects of delays and packet loss challenges [10]. ...
The high rate of increase in the number of threats experienced in multimedia has led to its reduction in the number of its subscribers. This number of threats observed in multimedia that has drastically led to the reduction of its subscribers is eradicated by an introduction of improving security management in a multimedia environment using the neuro-fuzzy controller.
... Wireless ad networks represent live streaming systems that are fully distributed without infrastructure [7]. Significant disruption occurs when multiple transfers occur with links to the same or different codes, thus leading to additional problems and issues such as delay, jitter, limited bandwidth, packet loss (packet loss), etc., which also affects service level (QoS) [8].Over the past few years, wireless networks have attracted a lot of research across the network and social functioning [9]. Recently, multimedia programs on ad hoc wireless have become increasingly common, but even largely the effects of delays and packet loss challenges [10]. ...
The rate at which hackers have devised means of increasing threats is becoming unbearable. Classified information is no longer confidential in financial institutions and academic environments. Government agencies and election organizers are no exception in these nefarious activities. The resultant effect is a decline in the number of subscribers that patronize the affected telecommunication companies. The threats could be minimized or prevented by introducing a smart means of checking to eliminate the threats to improve the security management in the higher institution or multimedia environment using intelligent agents.
... Such definition is suitable for many industries as outlined, for example, in [6,7]. It also allows application of Mamdani-Type or Sugeno-Type fuzzy inference systems for obtaining the consolidated risk levels as described by [1,11,9]. This process is similar to different other practical applications provided in [2]. ...
... [14], investigate equity market data prediction is developed based on neural network and neuro fuzzy model by using the past equity market data. [18], propose a Sugeno-type fuzzy inference system for stock price prediction using technical indicators as its input values. The study explores Sugeno-type fuzzy inference engine to optimize the estimated result. ...
... We choose a momentum constant, ω, which is small in relation to the value of ηδ o x . In training our fuzzy-neural network, the output weights vector components are updated using equation 18. (18) Where n is the training cycle (epochs). w kj (n) is the weight between the output and hidden neurons at epoch (n), w kj (n+1) is the weight between the output and hidden neurons at epoch (n+1), η is the Learning rate factor, δ o k is the output error signal, called the local gradient. ...
... Membership functions are constructed for each input variable. A total of 108 sample data sets are obtained through fuzzy inference system developed in [18]. ...
In this paper, Fuzzy logic and Neural Network approaches for predicting financial stock price are investigated. A study of a knowledge based system for stock price prediction is carried out. We explore Trapezoidal membership function method and Sugeno-type fuzzy inference engine to optimize the estimated result. Our model utilizes the performance of artificial neural networks trained using back propagation and supervised learning methods respectively. The system is developed based on the selection of stock data history obtained from Nigerian Stock Exchange in Nigeria, which are studied and used in training the system. A computer simulation is designed to assist the experimental decision for the best control action. The system is developed using MySQL, NetBeans, Java, and MatLab. The experimental result shows that the model has such properties as fast convergence, high precision and strong function approximation ability. It has shown to perform well in the context of various trading strategies involving stocks.
This paper deals with solutions for numeric evaluation of risks containing several different risk factors assessed by experts. The proposed methods can be used to assess the risks and obtain the risk scores in different industries, including financial industry, but they are also suitable for assessing risks in other areas, e.g. project management. While risk is usually considered as a function of probability and impact with strong quantitative background, there are many practical cases when only qualitative risk assessment based on expert opinions can be used. At the same time there are still requirements and needs for applying numerical values and mathematical models to such qualitative assessments. We consider the options for aggregation of risk levels for corresponding risk factors and obtaining consolidated risk level using transparent and self-explanatory approach. The proposed models are constructed using maximum t-conorm and Łukasiewicz t-conorm. Practical example is provided for calculation of consolidated risk score.
Stock Market Prediction (SMP) is one of the most important and hottest topics in business and finance. The main goal of SMP is to develop an efficient technique to predict stock values and achieves accurate results with minimum number of input data. This research paper reviews currently available SMP techniques based on soft computing and bio inspired computing algorithms. Many issues in-volved in the SMP are identified and different techniques are studied along with their merits and demerits to find the most suitable one. This paper also analyses the performance of various techniques with respect to some metrics including MSE, RMSE, MAD, MAPE, AAE and Hit ratio. The reviewed papers are classified in terms of number of input variables, prediction method and evaluation parame-ters used. A tabular representation of all the SMP techniques is presented to facilitate the future comparison. From the reviewed paper, it is noticed that the integration of soft computing with the bio inspired algorithms has the potential to predict the stock market index with high accuracy and achieves best result than soft computing method alone.
