The purpose of this research work is to evaluate the use of statistical tools, specifically Ordinary Least Squares (OLS) and Artificial Neural Networks (ANN) and with the help of these tools to be able to independently and effectively predict the costs. of production in the context of supply logistics in the Peruvian paper industry. Both models that turn out to be different in their analysis, however, turn out to be complementary for a more exact and precise result, highlighting the ANNs for their superior performance in the precision of the evaluated metrics, where they managed to achieve an RMSE of 0.0171 and a MAE of 0.0122 compared to the OLS statistical model that achieved an RMSE of 0.0181 and a MAE of 0.2070. Likewise, the analysis between the dimensions studied, purchasing management stands out with a negative coefficient of -0.4978, which shows that its optimization will generate a positive impact on production costs, contrary to the case with the other two dimensions, which are: storage management and inventory management, which resulted in positive coefficients (0.7457 and 0.4667), which shows that their optimization does not necessarily generate a positive impact on production costs, but quite the opposite, that their inadequate management On the contrary, it can harm production costs. These results highlight the inherent need that Peruvian paper companies must have in being able to implement updated logistics systems, capable of integrating advanced statistical tools such as the use of ANN and MCO, which can scientifically help better decision making, allowing thereby improving your supply processes and thus being able to reduce your production costs.

The focus of this research is to analyze how supply chains’ management affects production costs in the cardboard and Packaging sector in Peru, specifically through the creation of artificial neural networks (ANN) to improve the logistical activities. Non-experimental quantitative design was applied, collected the data from the Year 2020 to the Year 2024 and sought to assess variables such as supplier capacities, stocks held, bottom line costs incurred and stock out ratios. The study revealed that there exists a proportionate inverse relationship between the logistical costs and production costs, proving that as the cost of acquiring goods needed for production as well as the cost of keeping and managing stock decreases, the overall production cost also decreases significantly. The ANN model was able to perform cost predictions with a high degree of accuracy which points out the relevance of sophisticated instruments in the shift of the supply chain. Also, it is important to note the core contribution of the research – effective logistics management is emphasized as a way of increasing competition in industries where supply chains are of critical importance. This research reinforces the effectiveness of designing ANN in minimizing costs, while adding knowledge to the reporting practice of the companies aimed at bettering their costs. The results are a good contribution in terms of technological change in logistics aimed at helping the organizations remain flexible in a changing economy.

In this paper, computational intelligence technique are presented for solving multi-point nonlinear boundary value problems based on artificial neural networks, evolutionary computing approach, and active-set technique. The neural network is to provide convenient methods for obtaining useful model based on unsupervised error for the differential equations. The motivation for presenting this work comes actually from the aim of introducing a reliable framework that combines the powerful features of ANN optimized with soft computing frameworks to cope with such challenging system. The applicability and reliability of such methods have been monitored thoroughly for various boundary value problems arises in science, engineering and biotechnology as well. Comprehensive numerical experimentations have been performed to validate the accuracy, convergence, and robustness of the designed scheme. Comparative studies have also been made with available standard solution to analyze the correctness of the proposed scheme.

In the area of financial stock market forecasting, many studies have focused on application of Artificial Neural Networks (ANNs). Due to its high rate of uncertainty and volatility, the stock markets returns forecasting by conventional methods became a difficult task. The ANNs is a relatively new and have been reported as good methods to predict financial stock market levels and can model flexible linear or non-linear relationship among variables. The aim of the study is to employ an ANN models to estimate and predict the dynamic volatility of the daily of S & P500 market returns. Results of ANN models will be compared with time series model using GARCH family models. The use of the novel model for conditional stock markets returns volatility can handle the vast amount of nonlinear data, simulate their relationship and give a moderate solution for the hard problem. The forecasts of stock index returns in the paper will be evaluated and compared, considering the MSE, RMSE and MAE forecasts statistic.

Construction sites are accident-prone locations and therefore safety management plays an im-portant role in these workplaces. This study presents an adaptive algorithm for performance as-sessment of project management with respect to resilience engineering and job security in a large construction site. The required data are collected using questionnaires in a large construction site. The presented algorithm is composed of radial basis function (RBF), artificial neural networks multi-layer perceptron (ANN-MLP), and statistical tests. The results indicate that preparedness, fault-tolerance, and flexibility are the most effective factors on overall efficiency. Moreover, job security and resilience engineering have similar statistical impacts on overall system efficiency. The results are verified and validated by the proposed algorithm.

In this study, the backpropagation neural network (BPNN) is tested for the ability to forecast the daily volatility of two stock market indices from the Middle East and North Africa (MENA) region using volume; namely Morocco and Saudi Arabia. Volatility series were estimated using the Exponential Auto-Regressive Conditional Heteroskedasticity (EGARCH) model. The simulation results show that trading volume helps improving the forecasting accuracy of BPNN in Morocco but not in Saudi Arabia. As a result, volume represents valuable information flow to be used in the modeling and prediction of volatility in Morocco. In addition, it is found that BPNN overpredicts volatility during high volatile periods. This finding is important in financial applications such as asset allocation and derivatives pricing.

In this paper, the problem of predicting the exchange rate time series in the foreign exchange rate market is going to be solved using a time-delayed multilayer perceptron neural network with gold price as external factor. The input for the learning phase of the artificial neural network are the exchange rate data of the last five days plus the gold price in two different currencies of the exchange rate as the external factor for helping the artificial neural network improving its forecast accuracy. The five-day delay has been chosen because of the weekly cyclic behavior of the exchange rate time series with the consideration of two holidays in a week. The result of forecasts are then compared with using the multilayer peceptron neural network without gold price external factor by two most important evaluation techniques in the literature of exchange rate prediction. For the experimental analysis phase, the data of three important exchange rates of EUR/USD, GBP/USD, and USD/JPY are used.

In financial industry, the accurate forecasting of the stock market is a major challenge to optimize and update portfolios and also to evaluate several financial derivatives. Artificial neural networks and technical analysis are becoming widely used by industry experts to predict stock market moves. In this paper, different technical analysis measures and resilient back-propagation neural networks are used to predict the price level of five major developed international stock markets, namely the US S & P500, Japanese Nikkei, UK FTSE100, German DAX, and the French CAC40. Four categories of technical analysis measures are compared. They are indicators, oscillators, stochastics, and indexes. The out-of-sample simulation results show a strong evidence of the effectiveness of the indicators category over the oscillators, stochastics, and indexes. In addition, it is found that combining all these measures lead to an increase of the prediction error. In sum, technical analysis indicators provide valuable information to predict the S & P500, Nikkei, FTSE100, DAX, and the CAC40 price level.