Accurate Stock Market Prediction Method Based on Ant Lion Optimization Machine Learning

Ant lion optimization for short-term wind integrated hydrothermal power generation scheduling

The investment banking and financial sectors have undergone significant transformation from the 19th century to the present, driven by technological advancements and evolving trading strategies. Traditional methods of buying and selling stocks have been replaced or supplemented by automated algorithms and machine learning techniques, enabling more precise stock market predictions. This review paper consolidates historical and contemporary strategies employed by traders and investors to maximize profits in the stock market. It emphasizes the application of machine learning in predicting stock market trends and decision-making for buying and selling securities. A systematic review of journal articles published between 2016 and 2022 was conducted to identify the primary markets, stock indices, and trading strategies utilized in stock market predictions. The paper contributes to the literature by providing (1) a detailed analysis of trading strategies and market indicators, and (2) a comprehensive review of machine learning techniques employed in stock market forecasting. Furthermore, a bibliometric analysis highlights the most influential studies in this domain. Technical analysis tools, such as moving averages and candlestick patterns, are explored alongside modern methodologies. The study also identifies existing gaps in trading strategy research, offering insights for future advancements in this field. This review serves as a valuable resource for understanding the intersection of traditional trading methods, machine learning algorithms, and stock market prediction.

Abstract: Stock market forecasting remains a major concern to investors, financial institutions, and traders. Most classical forecasting techniques such as statistical modelling and technical analysis generally fail to account for the complexity and non-linearity of financial markets. Recently, neural networks, a new-age branch of machine learning, have emerged as a powerful weapon for better forecasting in the stock market. Neural networks, especially deep learning models such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM), are most suited to learning complex patterns from the historical data and reveal hidden correlations or relationships between different variables which have not been captured by the traditional models. The article discusses the role of neural networks in predicting stock market trends and the applications of these models in financial forecasting. The fundamentals of neural networks are explored, their special applications in stock market prediction, and the advantages they confer over traditional techniques. The objective of this article is to also provide insights into key obstacles, including data quality, overfitting, and interpretability, which can impinge upon the effective use of neural networks in finance. Case studies and simulated situations help present neural networks' use, where they are positioned to enhance stock market prediction output with accuracy and reliability. It seems that future directions that research in this field will take would involve integration with different alternative data sources, with quantum computing anticipated to change the landscape of financial prediction models. The insights provided... Keywords: Neural Networks, Stock Market Predictions, Machine Learning, Financial Forecasting, Trend Analysis, Deep Learning, Predictive Analytics, Data Sciences, and Algorithmic Trading.

Stock market prediction is a crucial and challenging task due to its nonlinear, evolutionary, complex, and dynamic nature. Research on the stock market has been an important issue for researchers in recent years. Companies invest in trading the stock market. Predicting the stock market trend accurately will minimize the risk and bring a maximum amount of profit for all the stakeholders. During the last several years, a lot of studies have been done to predict stock market trends using Traditional, Machine learning and deep learning techniques. This survey will assist the readers & researchers in selecting algorithms that can be useful for a predicting the stock market. A survey of various algorithms and its parameters for stock market prediction is presented in this paper.

Stock market trends can be affected by external factors such as public sentiment and political events. The goal of this research is to find whether or not public sentiment and political situation on a given day can affect stock market trends of individual companies or the overall market. For this purpose, the sentiment and situation features are used in a machine learning model to find the effect of public sentiment and political situation on the prediction accuracy of algorithms for 7 days in future. Besides, interdependencies among companies and stock markets are also studied. For the sake of experimentation, stock market historical data are downloaded from Yahoo! Finance and public sentiments are obtained from Twitter. Important political events data of Pakistan are crawled from Wikipedia. The raw text data are then pre-processed, and the sentiment and situation features are generated to create the final data sets. Ten machine learning algorithms are applied to the final data sets to predict the stock market future trend. The experimental results show that the sentiment feature improves the prediction accuracy of machine learning algorithms by 0–3%, and political situation feature improves the prediction accuracy of algorithms by about 20%. Furthermore, the sentiment attribute is most effective on day 7, while the political situation attribute is most effective on day 5. SMO algorithm is found to show the best performance, while ASC and Bagging show poor performance. The interdependency results indicate that stock markets in the same industry show a medium positive correlation with each other.

Orthogonal frequency-division multiplexing [OFDM] is an information transfer technique in which a single data flow is divided between several closely spaced narrowband subchannel frequency range rather than a single Wideband channel frequency. The information is sent to the relay node there is a delay and some data is lost in the relay node is the major issue in the existing system. To overcome these challenges, The objective of this study is to minimize the overall energy consumption and to maximize the network lifetime. In this paper, a novel Five Input Hybrid Optimization Relay Node Selection and Energy Efficient Routing (FIHORNSEER) technique has been proposed for choosing the best relay based on noises. Ant Lion Optimization (ALO) is initially utilized to select the relay node's elite position. Secondly, the Crow Search Optimization (CSO) Algorithm is used for the phenomenon of position and memory of each relay. Finally, the Memetic Algorithm (MA) was generated by integrating the Ant Lion and Crow search optimization algorithm for the best relay node selection. The proposed framework is compared with previous techniques like FRNSEER, LMMSE, and HABO-OFDM Methods in terms of performance analysis, such as average utility, Energy Consumption, and Network Life Time. The result shows that the proposed FIHORNSEER improves the energy consumption better than 22.01%, 16.4%, and 12.2% FRNSEER, LMMSE, and HABO-OFDM, respectively.

In order to solve the limitations of ant lion optimization algorithm such as local optimum slow convergence speed and so on this paper applies optimization strategy Logistic chaotic map and reverse learning to improve the selection of random ant lion update ant position and elite ant lion respectively. The improved ant lion optimization algorithm is compared and analyzed by selecting standard test functions, and the optimization accuracy and convergence speed of the algorithm are obviously improved. The improved ant lion optimization algorithm combined with a series of pipe routing engineering rules is applied to the pipe routing of aeroengine. The simulation of a pipe routing example is carried out by Siemens NX11.0 Grip and MATLAB, and the effectiveness of the proposed method is verified again.

The Antlion Optimization (ALO) algorithm is a meta-heuristic optimization algorithm based on the hunting of ants by antlions. The basic inadequacy of this algorithm is that it has long run time because of the random walk model used for the ant's movement. We improved some mechanisms in ALO algorithm, such as ants' random walking, reproduction, sliding ants towards antlion, elitism, and selection procedure. This proposed algorithm is called Improved Antlion Optimization (IALO) algorithm. To show the performance of the proposed IALO algorithm, we used different measurement metrics, such as mean best, standard deviation, optimality, accuracy, CPU time, and number of function evaluations (NFE). The proposed IALO algorithm was tested for different benchmark test functions taken from the literature. There are no studies regarding time analysis of ALO algorithm found in the literature. This study firstly aims to demonstrate the success of the proposed IALO algorithm especially in runtime analysis. Secondly, the IALO algorithm was also applied to the Quadratic Assignment Problem (QAP) known as a difficult combinatorial optimization problem. In QAP tests, the performance of the IALO algorithm was compared with the performances of the classic ALO algorithm and 14 well-known and recent meta-heuristic algorithms. The results of the benchmark test functions show that IALO algorithm is able to provide very competitive results in terms of mean best/standard deviation, optimality, accuracy, CPU time and NFE metrics. The CPU time results prove that IALO algorithm is faster than the classic ALO algorithm. As a result of the QAP tests, the proposed IALO algorithm has the best performance according to the mean cost, worst cost and standard deviation. The source codes of QAP with the proposed IALO algorithm are publicly available at https://github.com/uguryuzgec/QAP-with-IALO.

Development of an Enhanced Ant Lion Optimization Algorithm and its Application in Antenna Array Synthesis

Predicting heat transfer rate of a ribbed triple-tube heat exchanger working with nanofluid using neural network enhanced by advanced optimization algorithms

Stock market prediction is of great interest to stock traders and applied researchers. Main issues in developing a fully automated stock market prediction system are: feature extraction from the stock market data, feature selection for highest prediction accuracy, the dimensionality reduction of the selected feature set and the accuracy and robustness of the prediction system. In this paper, an automated decision tree-adaptive neuro-fuzzy hybrid automated stock market trend prediction system is proposed. The proposed system uses technical analysis (traditionally used by stock traders) for feature extraction and decision tree for feature selection. Selected features are then subjected to dimensionality reduction and the reduced dataset is then applied to the adaptive neuro-fuzzy system for the next-day stock market trend prediction. The proposed system is tested on four major international stock markets. The results show that the proposed hybrid system produces much higher accuracy when compared to stand-alone decision tree based system and ANFIS based system without feature selection and dimensionality reduction.

Power losses and voltage deviations in distribution power networks (DPNs) are high since they carry more power demand than transmission power networks. Also, voltage deviation beyond the allowable range causes voltage stability problems in the DPN. The power loss (PL) in the DPN should be kept at the minimum level for the economic operation of the electric grid. Integrating distributed generation (DG) in appropriate sites of the power networks can minimize the power losses and voltage drops. An integrated optimization approach is proposed in this paper, by combining an analytical and metaheuristic algorithm to optimize the placement and sizing of multiple DGs. The active power loss sensitivity (APLS) index is an analytical mathematical computation approach used to identify the optimal bus locations for DG placement. The modified ant lion optimization (MALO) algorithm is applied to optimize the ratings of the DG systems. The MALO algorithm is proposed by adopting the Lévy flights (LF) pattern in the random walk process (RWP). LF representation of RWPs enhances the exploration phase of the ALO algorithm and helps to obtain the near-optimal solution. The proposed integrated approach optimizes multiple units of photovoltaic (PV) and wind turbine (WT) units to minimize the multi-objective function, including AP loss and voltage deviation (VD) minimizations. The effectiveness of the proposed integrated approach is validated on the IEEE 69-bus, 85-bus, and 118-bus radial DPNs. Besides, the simulation study is extended for ant lion optimization (ALO), BAT, and artificial bee colony (ABC) algorithms-based techniques. The integrated approach has reduced the total AP loss of the IEEE 69-bus and 85-bus radial DPN from 225 kW to 70.51 kW and 316.12 kW to 162.80 kW, respectively, for the optimized three PV DG units allocation. Likewise, the total AP loss of the 118-bus radial DPN is cut down from 1296.3 kW to 432.3 kW after the optimized five PV DG units allocation. Meanwhile, the total AP LOSS of the 69-bus, 85-bus, and 118-bus radial DPNs is reduced to 4.78 kW, 53.87 kW, and 112.2 kW, respectively, after the optimized WT DG allocation. Additionally, the optimized inclusion of multiple DG units significantly minimized the VD of the DPNs. The minimum VD of the 69-bus, 85-bus, and 118-bus test systems is reduced from 0.0908 p.u., 0.1297 p.u., and 0.1312 p.u. to 0.0174 p.u., 0.0384 p.u., and 0.0201 p.u., respectively, for the multiple PV unit allocations. Similarly, the minimum VDs of the 69-bus, 85-bus, and 118-bus radial DPNs are minimized to 0.0048 p.u., 0.0190 p.u., and 0.0093 p.u., respectively, following the multiple WT DG unit allocations. The simulation findings of the APLS-MALO integrated approach are related to the various optimization techniques. The comparative study reveals that the proposed integrated approach gives a more effective and efficient solution than ALO, BAT, ABC, and other optimization techniques. Finally, the simulation findings of the APLS-MALO integrated technique are verified via the calculation of conventional statistical metrics and the conduction of a non-parametric Wilcoxon test.

Frame structures are widely used in engineering applications, especially in space structures. For special use such as shape and vibration control of such structures, piezoelectric patches are usually placed on the beam surfaces to form active frame structures. To perform shape control or vibration control tasks, modeling methods for the formed active frame structures need to be studied. This paper develops a new distributed model of an active frame structure composed of multilayer piezoelectric beam components. First, the governing equations of a beam, bonded with piezoelectric patches, are developed via the generalized Hamilton principle, by considering the transverse shear strain. Then, the analytical solutions of the governing equations and the generalized element stiffness matrix are derived through the distributed transfer function formulation. Finally, the analytical solution of the entire system is obtained by the technique for assembling element stiffness matrix. In numerical simulations, buckling and vibration of an active frame structure are both studied. In addition, a novel Improved Ant Lion algorithm is proposed for optimal design of the frame structures. The optimization examples confirm that the proposed algorithm is more efficient than other existing popular algorithms such as Genetic Algorithm (GA) and Ant Lion Optimization (ALO) algorithm.

The product design process has a very important effect on product costs. It aims to develop products that are able to compete by achieving an optimum design in the product design process. This research presents the first application in the literature of the grey wolf, whale, water cycle, ant lion and sine-cosine optimization algorithms for the optimum design of vehicle components. In this study, the optimal structural model of a vehicle connecting rod was determined. In the optimization process, various design alternatives were created by using the latin hypercube method. Stress analysis was performed for each of these designs. According to the generated responses, equations for objective and constraint functions were obtained. The optimization problem was solved using the above mentioned algorithms which have been newly developed in the literature, resulting in optimum connection rod design. The results demonstrate that the grey wolf, whale, water cycle, ant lion and sine-cosine algorithms are very important options in optimizing design and manufacturing optimization problems.

Ant lion optimizer (ALO) is a newly developed population-based search algorithm inspired by hunting mechanism of antlions and based on five steps of hunting the ants, i.e., the random walk of ants, building traps, entrapment of ants in traps, catching preys and re-building traps. This paper presents the application of ALO algorithm for the solution of non-convex and dynamic economic load dispatch problem of electric power system. The performance of ALO algorithm is tested for economic load dispatch problem of four IEEE benchmarks of small-scale power systems, and the results are verified by a comparative study with lambda iteration method, particle swarm optimization algorithm, genetic algorithm, artificial bee colony, evolutionary programming and Grey Wolf optimizer (GWO). Comparative results show that the performance of ant lion optimizer algorithm is better than recently developed GWO algorithm and other well-known heuristics and meta-heuristics search algorithms.