Comparison of Electricity Usage Forecasting Model Evaluation Based on Historical Load Dataset Duration Using Long Short-Term Memory Architecture

Forecasting stock prices has always been a complex and challenging task due to its high volatility, noise in data, and abrupt price fluctuations caused by different factors. Traditional approaches, such as quantitative, fundamental, and technical analysis, often struggle to accurately predict stock price movements due to their difficulty in processing non-linear data. The evolution of machine learning, particularly neural network models, opened new opportunities for improving prediction accuracy by handling non-linear and multidimensional data with high effectiveness. This study focuses on evaluating and comparing three neural network architectures, in which the last is a combination of the first two - Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-LSTM model, for forecasting stock prices. Using ten years of historical stock data, taken for Apple Inc. (AAPL) stocks as an example, ranging from 2015 to 2025, the models were trained and tested on key performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R². Results show that while both CNN and LSTM models show good performance individually, the hybrid CNN-LSTM model can significantly outperform them, achieving the highest accuracy with the lowest error rates. By combining the strengths of CNN for feature extraction and LSTM for temporal sequence processing, the hybrid model effectively captures complex patterns in stock price movements. By iterating over the types of layers to use, we came to the conclusion, that by combining both models into one hybrid model, some layers, like one CNN layer, and one LSTM layer should be removed. This research demonstrates the potential of hybrid neural network models in financial time-series forecasting and comprehensively analyzes their advantages over non-hybrid models.

Stocks have become one of the largest and most intricate financial markets globally due to their high popularity, making them very challenging to predict as they can process millions of transactions rapidly. The objective of this study is to enhance the field by creating a dependable and accurate model for predicting the stock price of Amazon. This will be achieved via the use of advanced algorithms such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). This research utilised historical data on Amazon's stock price from the past five years, which was acquired from Yahoo Finance. The data was partitioned using a hold-out validation technique, allocating 80% for training and 20% for testing. The model underwent training using different optimizers (Adam, SGD, RMSprop), batch sizes (8, 16, 32), and learning rates (0.001, 0.0001). The evaluation criteria comprised of mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The results suggest that the GRU model, when trained with the RMSprop optimizer using a batch size of 16 and a learning rate of 0.0001, as well as with the SGD optimizer using a batch size of either 16 or 32 and a learning rate of either 0.001 or 0.0001, produced the lowest error metrics, indicating superior performance. This study enables more precise forecasts of stock prices and more efficient investment techniques.

Compressive strength is an important mechanical property of high-strength concrete (HSC), but testing methods are usually uneconomical, time-consuming, and labor-intensive. To this end, in this paper, a long short-term memory (LSTM) model was proposed to predict the HSC compressive strength using 324 data sets with five input independent variables, namely water, cement, fine aggregate, coarse aggregate, and superplasticizer. The prediction results were compared with those of the conventional support vector regression (SVR) model using four metrics, root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient (R2). The results showed that the prediction accuracy and reliability of LSTM were higher with R2 = 0.997, RMSE = 0.508, MAE = 0.08, and MAPE = 0.653 compared to the evaluation metrics R2 = 0.973, RMSE = 1.595, MAE = 0.312, MAPE = 2.469 of the SVR model. The LSTM model is recommended for the pre-estimation of HSC compressive strength under a given mix ratio before the laboratory compression test. Additionally, the Shapley additive explanations (SHAP)-based approach was performed to analyze the relative importance and contribution of the input variables to the output compressive strength.

BackgroundAccurate incidence prediction of sexually transmitted diseases (STDs) is critical for early prevention and better government strategic planning. In this paper, four different forecasting models were presented to predict the incidence of AIDS, gonorrhea, and syphilis.MethodsThe annual percentage changes in the incidence of AIDS, gonorrhea, and syphilis were estimated by using joinpoint regression. The performance of four methods, namely, the autoregressive integrated moving average (ARIMA) model, Elman neural network (ERNN) model, ARIMA-ERNN hybrid model and long short-term memory (LSTM) model, were assessed and compared. For 1-year prediction, the collected data from 2011 to 2020 were used for modeling to predict the incidence in 2021. For 5-year prediction, the collected data from 2011 to 2016 were used for modeling to predict the incidence from 2017 to 2021. The performance was evaluated based on four indices: mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).ResultsThe morbidities of AIDS and syphilis are on the rise, and the morbidity of gonorrhea has declined in recent years. The optimal ARIMA models were determined: ARIMA(2,1,2)(0,1,1)12, ARIMA(1,1,2)(0,1,2)12, and ARIMA(3,1,2)(1,1,2)12 for AIDS, gonorrhea, and syphilis 1-year prediction, respectively; ARIMA (2,1,2)(0,1,1)12, ARIMA(1,1,2)(0,1,2)12, and ARIMA(2,1,1)(0,1,0)12 for AIDS, gonorrhea and syphilis 5-year prediction, respectively. For 1-year prediction, the MAPEs of ARIMA, ERNN, ARIMA-ERNN, and LSTM for AIDS are 23.26, 20.24, 18.34, and 18.63, respectively; For gonorrhea, the MAPEs are 19.44, 18.03, 17.77, and 5.09, respectively; For syphilis, the MAPEs are 9.80, 9.55, 8.67, and 5.79, respectively. For 5-year prediction, the MAPEs of ARIMA, ERNN, ARIMA-ERNN, and LSTM for AIDS are 12.86, 23.54, 14.74, and 25.43, respectively; For gonorrhea, the MAPEs are 17.07, 17.95, 16.46, and 15.13, respectively; For syphilis, the MAPEs are 21.88, 24.00, 20.18 and 11.20, respectively. In general, the performance ranking of the four models from high to low is LSTM, ARIMA-ERNN, ERNN, and ARIMA.ConclusionThe time series predictive models show their powerful performance in forecasting STDs incidence and can be applied by relevant authorities in the prevention and control of STDs.

A CNN encoder decoder LSTM model for sustainable wind power predictive analytics

Accurate prediction of energy consumption in smart homes is essential for optimizing energy usage, reducing operational costs, and enhancing occupant comfort. Traditional statistical and machine learning models often struggle to capture the complex spatiotemporal patterns inherent in energy usage data. To address this limitation, this study proposes a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model for forecasting energy consumption in smart homes, combining the spatial feature extraction strengths of Convolutional Neural Networks (CNNs) with the temporal learning capabilities of Long Short-Term Memory (LSTM) networks. The model demonstrated high predictive accuracy and generalization, as reflected by the evaluation metrics: Mean Absolute Error (MAE) = 0.0325, Mean Squared Error (MSE) = 0.0031, Root Mean Squared Error (RMSE) = 0.0557, and Mean Absolute Percentage Error (MAPE) = 0.2054. However, as the model was trained on synthetic data, further validation using real-world energy consumption datasets is necessary to assess its practical applicability and robustness.

This chapter aims to predict the foreign currency exchange rate on the basis of the US dollar over twenty-two different currencies. This chapter proposes two machine learning algorithms like Support Vector Regression (SVR), Random Forest Regression (RFR) and one deep learning algorithm named Long Short-Term Memory (LSTM), for the technical analysis of currency exchange rate prediction. The authors use Mean absolute error (MAE), Mean squared error (MSE), Root Mean Squared Error (RMSE), and mean absolute percentage error (MAPE) to measure the performance of the algorithms. Empirical findings specify that the overall performance of the algorithms is outstanding, but the Long Short-Term Memory (LSTM) shows less error than others. This study is useful for the stakeholders to set a wide range of approaches for the foreign exchange market.KeywordsCurrency exchange rate predictionMachine learningDeep learningTime series analysis

Prediction of dissolved oxygen in a fishery pond based on gated recurrent unit (GRU)

Experiments have proven that traditional prediction research methods have limitations in practice. Proposing countermeasures for environmental changes is the key to optimal control of the cold chain environment and reducing the lag of control effects. In this paper, a cold chain transportation environment prediction method, combining k-means++ and a long short-term memory (LSTM) neural network, is proposed according to the characteristics of the cold chain transportation environment of agricultural products. The proposed prediction model can predict the trend of cold chain environment changes in the next ten minutes, which allows cold chain vehicle managers to issue control instructions to the environmental control equipment in advance. The fusion process for temperature and humidity data measured by multiple data sensors is performed with the k-means++ algorithm, and then the fused data are fed into an LSTM neural network for prediction based on time series. The prediction error of the prediction model proposed in this paper is very satisfactory, with a root-mean-square error (RMSE), mean absolute error (MAE), mean squared error (MSE), mean absolute percentage error (MAPE) and R-squared of 0.5707, 0.2484, 0.3258, 0.0312 and 0.9660, respectively, for temperature prediction, and with an RMSE, MAE, MSE, mean absolute percentage error and R-squared of 1.6015, 1.1770, 2.5648, 0.2736 and 0.9702, respectively, for humidity prediction. Finally, the LSTM neural network and back propagation (BP) neural network are compared in order to enhance the reliability of the results. In terms of the prediction effect of the temperature and humidity in cold chain vehicles transporting agricultural products, the proposed model has a higher prediction accuracy than that of existing models and can provide strategic support for the fine management and regulation of the cold chain transportation environment.

Nowadays, air quality is a major issue, especially in large cities. Apart from air pollution, particulate matter (PM), especially PM2.5, poses serious health risks to individuals with respiratory conditions. Accurate forecasting of PM levels is crucial to warn vulnerable populations and reduce exposure. Machine learning models can effectively predict PM concentrations based on historical data and barometric conditions such as temperature and humidity. Such predictions can support timely public health interventions and environmental policy decisions. The selection of the optimal machine learning model for time series forecasting requires a careful balance between predictive accuracy and computational efficiency. This study evaluates a number of widely used models, such as Random Forest (RF), Long Short-Term Memory (LSTM), Convolutional Neural Network-LSTM (CNN–LSTM), Extreme Gradient Boosting (XGB/HistGradientBoosting), and hybrid approaches (LSTM embeddings + RF), in the context of time series forecasting for particulate matter (PM) concentrations. Performance is assessed using three key error metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Scaled Error (MASE). Additionally, the computational demands and development complexity of each model are analyzed. The overall results are of great interest for each application model, and in more detail, it is shown that the best compromise between accuracy and efficiency can be achieved, while a corresponding prediction model with satisfactory predictive performance can be implemented. The results show that CNN–LSTM and hybrid approaches provide high accuracy, while tree-based models are computationally efficient, offering practical options for real-time forecasting systems.

The movement of gold prices serves as a critical indicator in investment decision-making, especially in dynamic and uncertain market conditions. This study aims to develop a gold price prediction model based on Long Short-Term Memory (LSTM), a type of Recurrent Neural Network (RNN) capable of capturing temporal patterns in historical price data. The goal of implementing this model is to generate more accurate predictions compared to conventional methods, thereby supporting more informed investment decisions. The research utilizes daily gold price data over a specific period, combined with other economic indicators such as oil prices, exchange rates, and interest rates. The data undergoes preprocessing steps, including normalization and division into training, validation, and testing sets. The proposed model architecture consists of a single LSTM layer with 64 neurons and an output layer, trained over 50 epochs with a batch size of 32. The results show that the LSTM model achieves high prediction accuracy. This is demonstrated by evaluation metrics including a Mean Absolute Error (MAE) of 26.12, Mean Squared Error (MSE) of 1269.15, Root Mean Squared Error (RMSE) of 35.63, and an R² score of 0.9858, indicating that the model can explain 98.58% of the variance in actual gold price data. Furthermore, the visualization of the results indicates that the model is capable of closely following gold price trends and consistently predicting upward price movements over the next 30 days. The model has also been successfully implemented into a web-based platform using TensorFlow.js, enabling users to access real-time predictions in an efficient and responsive manner.

Cryptocurrencies have gained immense popularity in recent years as an emerging asset class, and their prices are known to be highly volatile. Predicting cryptocurrency prices is a difficult task due to their complex nature and the absence of a central authority. In this paper, our proposal is to employ Long Short-Term Memory (LSTM) networks, a type of deep learning technique to forecast the prices of cryptocurrencies. We use historical price data and technical indicators as inputs to the LSTM model, which learns the underlying patterns and trends in the data. To improve the accuracy of the predictions, we also incorporate a Change Point Detection (CPD) technique using the Pruned Exact Linear Time (PELT) algorithm. This method allows us to detect significant changes in cryptocurrency prices and adjust the LSTM model accordingly, leading to better predictions. We evaluate our approach predominantly on Bitcoin cryptocurrency, but the model can be implemented on other cryptocurrencies provided there are valid historical price data. Our experimental results show that our proposed model outperforms the baseline LSTM algorithm, achieving higher accuracy and better performance in terms of Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE). Our research findings suggest that combining deep learning techniques such as LSTM with change point detection techniques such as PELT can improve cryptocurrency price prediction accuracy and have practical implications for investors, traders, and financial analysts.

A novel wavenets long short term memory paradigm for wind power prediction

This study aims to create a monthly sales quantity budget by making use of the previous income data of an enterprise operating within the construction sector, which is considered the locomotive of the economy. For estimating time-series of sales as a linear model ARIMA (Auto-Regressive Integrated Moving Average), as nonlinear model LSTM (Long ShortTerm Memory) and a HYBRID (LSTM and ARIMA) model built to improve system performance compared to a single model was used. As a result of the study, Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE) values obtained from each of the methods used in the application were compared, and a monthly sales volume budget was created for 2017 with all the methods used. When the MAPE and MSE values obtained from each of these methods were compared, the best performance was the Hybrid model that gave the lowest error, and in addition, the fact that all of the application models got very realistic results by using the historical data showed the success of the predictions.

Accurate electrical load forecasting is of great significance to help power companies in better scheduling and efficient management. Since high levels of uncertainties exist in the load time series, it is a challenging task to make accurate short-term load forecast (STLF). In recent years, deep learning approaches provide better performance to predict electrical load in real world cases. The convolutional neural network (CNN) can extract the local trend and capture the same pattern, and the long short-term memory (LSTM) is proposed to learn the relationship in time steps. In this paper, a new deep neural network framework that integrates the hidden feature of the CNN model and the LSTM model is proposed to improve the forecasting accuracy. The proposed model was tested in a real-world case, and detailed experiments were conducted to validate its practicality and stability. The forecasting performance of the proposed model was compared with the LSTM model and the CNN model. The Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) were used as the evaluation indexes. The experimental results demonstrate that the proposed model can achieve better and stable performance in STLF.