particle swarm algorithm

The effort of this article is to solve one of the main problems in the field of banking, which is closely related to the field of information technology. The combination of the management discussion of this topic with the field of information technology will be one of the important topics in the field of information technology management. The main goal of this article is the clustering of bank customers.At first, all customer characteristics were extracted from the bank's database, which was randomly extracted for 900,000 customers, which will be provided as input to the proposed method of this article. All the characteristics of these customers were extracted and 10 characteristics (except four characteristics of the LRFM method) were listed using the opinions of experts. The proposed method should be able to choose among these 10 features for clustering customers, which results in more resolution in clustering. Due to the high number of cases of this problem, it is not possible to do it manually, and the proposed method tries to provide a separate model for clustering for the customers of each bank by examining different cases. Also, the problem of choosing the right value for the number of clusters in the K-means method is solved by the method proposed in this article. The results show that it is better than the basic RFM and LRFM methods.Keywords: relationship management with bank customers, clustering, RFM model, LRFM model, particle swarm algorithm, K-means method.

The goal is to select an optimal portfolio of stocks by allocating capital among various investment opportunities in the stock market to achieve maximum return at a specified level of risk. This constitutes an efficient portfolio.

Attaining an efficient portfolio involves solving an optimization problem. There are numerous techniques and tools available to solve this issue. In this study, 15 stocks from companies listed on the Tehran Stock Exchange, including symbols such as Khapars, Khazamiya, Vepasar, Foulad, Akhabar, Kegel, Femli, Tapiko, Sepaha, Fazer, Fakhas, Shohbaran, Shefan, Qamro and Qathabat, were selected using cluster sampling. First, the daily returns of these stocks were calculated over a 5-year period from 2015 to 2020 (1183 days). The risk of the optimal investment portfolio was then calculated using the Mean-Semi Variance and Conditional Value at Risk models. These two criteria were compared using a classic solution method. Subsequently, the output data obtained from these calculations were compared using MATLAB software, employing the Particle Swarm Optimization algorithm under the Mean-Semi Variance risk criterion and the Genetic Algorithm under the Conditional Value at Risk criterion.

The results of this study indicate that the meta-heuristic Particle Swarm Optimization method yields a higher portfolio return ratio compared to the Genetic Algorithm in the Mean-Semi Variance risk criterion.

Originality / Value: 

This research utilizes multi-objective genetic algorithms and Particle Swarm Optimization, which are intelligent and novel algorithms, to minimize the objective function value using Conditional Value at Risk and Mean-Semi Variance criteria. These algorithms optimize the return and risk ratios of the stocks in the investment portfolio with the highest possible accuracy. Additionally, the efficiency comparison of these models using MATLAB software contributes an innovative aspect to this study.

Due to the increase in the volume of data and information in recent years, the issue of choosing the most appropriate feature for decision making has become very important. Classic attribute selection methods cannot work well on big data. Because feature selection is a complex problem, it seems appropriate to use meta-heuristic algorithms to solve this problem. In this paper, a new meta-heuristic algorithm inspired by nomadic migration to solve the feature selection problem is presented. This algorithm is named in honor of the Qashqai tribe. In this hybrid algorithm, the proportional function was designed based on the feature selection algorithm and based on minimizing the number of features and the amount of data error using neural network results. Then the Qashqai meta-heuristic algorithm was implemented on this fitness function and the results were compared with the well-known meta-heuristic algorithms of genetics and particle swarm. The results of the hypothesis test showed that the Qashqai optimization algorithm to solve the feature selection problem by the genetic algorithm and particle swarm is not defeated and in terms of convergence to the optimal solution works well.

In this paper a novel، bi-objective mixed-integer mathematical programming has been proposed for a distribution network problem. One objective function minimizes the total purchasing، transportation and holding costs and the another objective minimizes the total amount of delayed or before time deliveries multiplied by respective durations، named «JIT distribution». Supplying the customer demand، holding and delivering products at warehouse are the most important constraints considered in this model. This model has been designed for a three-echelon distribution network consisting multiple suppliers، wholesalers and retailers to distribute multiple products with a deterministic amount of demand through either direct or indirect channels in a planning horizon. Since real-sized problems of the resulting bi-objective mixed-integer linear programming (MILP) cannot be solved with exact methods، a multi objective particle swarm algorithm (MOPSO) is designed of which، quality in small-sized problems is compared with the solutions obtained by the LINGO software. The computational results show that the proposed MOPSO algorithm finds good solutions in shorter times than LINGO and has acceptable running times in large-scale problems.