Mean Absolute Percentage Error Values Research Articles

Improved forecasting of the compressive strength of ultra‐high‐performance concrete (UHPC) via the CatBoost model optimized with different algorithms

AbstractThis paper focuses on the applicability of CatBoost models constructed using various optimization techniques for improved forecasting the compressive strength of ultra‐high‐performance concrete (UHPC). Phasor particle swarm optimization (PPSO), dwarf mongoose optimization (DMO), and atom search optimization (ASO), which have been very popular recently, are preferred as optimization algorithms. A comprehensive and reliable data set is used to develop the CatBoost models, which include 785 test results with 15 input features. The performance of the CatBoost models (PPSO‐CatBoost, DMO‐CatBoost, and ASO‐CatBoost) optimized with different algorithms is thoroughly assessed by means of various statistical metrics and error analysis to determine the model with the best forecasting capability, and this model is compared with the models obtained from previous studies. In addition, Shapley additive exPlanations (SHAP) analysis is used to ensure the interpretability of the forecasting models and to overcome the “black box” problem of machine learning (ML) models. The obtained results demonstrate that all CatBoost models outstandingly forecast the compressive strength of UHPC. Among these models, the DMO‐CatBoost model stands out compared to the other models in various performance metrics, such as high coefficient of determination (R2) values, low root mean squared error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) values, along with a smaller error ratio. In other words, the RMSE, R2, MAPE, and MAE values of the DMO‐CatBoost model for the training set are 3.67, 0.993, 0.019, and 2.35, respectively, whereas those for the test set are 6.15, 0.978, 0.038, and 4.51. Additionally, the performance ranking of the algorithms used to optimize the hyperparameters of the CatBoost model is as follows: DMO > PPSO > ASO. On the other hand, SHAP analysis showed that age, fiber dosage, and cement dosage significantly influence the compressive strength of UHPC. These findings can guide structural engineers in the design and optimization of UHPC, thus assisting them in developing strategies to improve the strength properties of the material. Finally, based on the best forecasting model developed in this work, a graphical user interface has been developed to easily forecast the compressive strength of UHPC in practical applications without additional tools or software.

Advancing air quality forecasting in Abu Dhabi, UAE using time series models

This research enhances air quality predictions in Abu Dhabi by employing Autoregressive Integrated Moving Average (ARIMA) models on comprehensive air quality data collected from 2015 to 2023. We collected hourly data on nitrogen dioxide (NO2), particulate matter (PM10), and fine particulate matter (PM2.5) from 19 well-placed ground monitoring stations. Our approach utilized ARIMA models to forecast future pollutant levels, with extensive data preparation and exploratory analysis conducted in R. Our results found a significant drop in NO2 levels after 2020 and the highest levels of particulate matter observed in 2022. The findings of our research confirm the effectiveness of the models, indicated by Mean Absolute Percentage Error (MAPE) values ranging from 7.71 to 8.59. Additionally, our study provides valuable spatiotemporal insights into air pollution historical evolution, identifying key times and areas of heightened pollution, which can help in devising focused air quality management strategies. This research demonstrates the potential of ARIMA models in precise air quality forecasting, aiding in proactive public health initiatives and environmental policy development, consistent with Abu Dhabi’s Vision 2030.

Research and application of a novel grey multivariable model in port scale prediction under the impact of Free Trade Zone

Purpose Considering the impact of the Free Trade Zone (FTZ) policy on forecasting the port cargo throughput, this paper constructs a fractional grey multivariate forecasting model to improve the prediction accuracy of port cargo throughput and realize the coordinated development of FTZ policymaking and port construction.Design/methodology/approach Considering the effects of data randomization, this paper proposes a novel self-adaptive grey multivariate prediction model, namely FDCGM(1,N). First, fractional-order accumulative generation operation (AGO) is introduced, which integrates the policy impact effect. Second, the heuristic grey wolf optimization (GWO) algorithm is used to determine the optimal nonlinear parameters. Finally, the novel model is then applied to port scale simulation and forecasting in Tianjin and Fujian where FTZs are situated and compared with three other grey models and two machine learning models.Findings In the Tianjin and Fujian cases, the new model outperforms the other comparison models, with the least mean absolute percentage error (MAPE) values of 6.07% and 4.16% in the simulation phase, and 6.70% and 1.63% in the forecasting phase, respectively. The results of the comparative analysis find that after the constitution of the FTZs, Tianjin’s port cargo throughput has shown a slow growth trend, and Fujian’s port cargo throughput has exhibited rapid growth. Further, the port cargo throughput of Tianjin and Fujian will maintain a growing trend in the next four years.Practical implications The new multivariable grey model can effectively reduce the impact of data randomness on forecasting. Meanwhile, FTZ policy has regional heterogeneity in port development, and the government can take different measures to improve the development of ports.Originality/value Under the background of FTZ policy, the new multivariable model can be used to achieve accurate prediction, which is conducive to determining the direction of port development and planning the port layout.

Machine learning based data governance methods for demand response databases

With the increasing level of grid intelligence and the related demand response database expanding, it is important to study a compound problem data governance method for demand response, while the traditional data governance methods have problems such as not considering data temporality and ignoring the impact of noise and duplicate data on data repair. As a result, this project will develop an anomaly data extraction and repair model based on two-way long and short memory networks, and repair the anomaly data by respective noise smoothing, missing data filling, and duplicate data cleaning. The paper also provides an adaptive moment estimation approach for optimisation to raise the model’s accuracy. The outcomes demonstrated that the study model’s precision for anomalous data extraction was 100% and its recall rate was 80%, which was a significant improvement over the previous state. In terms of anomalous data repair, the research model had the root mean square error value and lowest mean absolute percentage error value when compared with related models, at 0.0049 MPa and 1.375% respectively. Both the abnormal data extraction and repair performance of the research model are greatly improved over the related models, and have important value in the abnormal data governance of demand response databases.

Evaluating geometric measurement accuracy based on 3D model reconstruction of nursery tomato plants by Agisoft photoscan software

Measuring the vegetation structure of a plant with the help of 3D images is a non-destructive method that can be used to monitor the plant’s status during the growing season. Structure from motion (SfM) is a popular optical distance measurement method that uses 2D images to create 3D models. Identifying factors that influence the precision of SfM is important due to its increasing use in phenotyping. The primary objectives of this study were, i) to scrutinize the impact of imaging parameters—including, color checkerboard location, overlap size of images, and background filtering—on the quality indices of 3D models, and ii) to attain precise measurements of leaf area, stem diameter, and height through the combination of images captured from different camera shooting angles. The three nursery tomato plants were photographed at every five-degree rotation of the turntable, five different locations of color checkerboards, and five camera shooting angles. Results indicated the color checkerboard’s presence and position affect the quality indices of the 3D models. Visually and by the lowest mean keypoint size value, the least noisy 3D model was obtained when the wall of the plant pot was covered with a checkerboard. When the base-to-distance (b/y) ratio as the image overlap index increased from 0.1 to 0.2, the generation time of the 3D models decreased by more than two times. Optimal Mean Absolute Percentage Error (MAPE) values of 1.08 %, 1.01 %, and 1.38 % were achieved for the estimation of leaf area, stem diameter, and height, respectively. This was recorded by using images taken at 0°, 30°, and 105° vertical azimuth angles. Constructing a 3D model by integrating images captured from other angles or more azimuth angles represents numerous visual challenges and leads to problems of point mismatch, which affects the accuracy of measurements.

Predicting hourly heating load in residential buildings using a hybrid SSA–CNN–SVM approach

This study proposes a hybrid prediction model using sparrow search algorithm (SSA) to optimize the convolutional neural network (CNN) and support vector machine (SVM), in order to perform accurate prediction of secondary supply temperature (Ts2). The historical operation data of Weifang residential building thermal station was adopted and reasonable data preprocessing was performed to suppress the interference of abnormal data. The input variables of the prediction model were screened using the correlation analysis method, taking the influence of the hysteresis effect into consideration. The SSA–CNN–SVM model was then developed for prediction. The performance of the model was evaluated by the root mean square error, mean absolute error, mean absolute percentage error (MAPE), and absolute value of relative error of each time step. The results obtained demonstrated that the SSA–CNN–SVM model has high prediction accuracy. The MAPE values of the two heat exchange stations were between 2.28 % and 2.4 %. The indoor temperature significantly affected the prediction accuracy of Ts2. After the introduction of the indoor temperature, the MAPE of the predicted values of the hybrid model was reduced by 0.35 %. The maximum reduction in MAPE of the SSA–CNN–SVM model was 1.5 % compared with other prediction models.

How good are different machine and deep learning models in forecasting the future price of metals? Full sample versus sub-sample

This study aims to forecast metal futures in commodity markets, including gold, silver, copper, platinum, palladium, and aluminium, using different machine and deep learning models. Prevalent models such as Stacked Long-Short Term Memory, Convolutional LSTM, Bidirectional LSTM, Support Vector Regressor, Extreme Gradient Boosting, and Gated Recurrent Unit are utilized. The model performance is assessed by multiple factors such as Root Mean Squared Error, Mean Absolute Error, and Mean Absolute Percentage Error. The study stands out by considering multiple metal commodity futures simultaneously, incorporating both Machine Learning and Deep Learning models, and conducting two sets of experiments with a full sample and subsample analysis. In addition, it uses different inputs of 30- and 60-days periods for robustness checks. Mean Absolute Percentage Error values suggest that different machine and deep learning models are efficient on prediction the future metal prices. However, the model performance varies significantly with the influence of metal choice, sample period, and inputs on prediction performance. Therefore, it suggests that constructing a theory based on machine and deep learning models is challenging.

Daily Streamflow Forecasting Using Networks of Real-Time Monitoring Stations and Hybrid Machine Learning Methods

Considering the increased risk of urban flooding and drought due to global climate change and rapid urbanization, the imperative for more accurate methods for streamflow forecasting has intensified. This study introduces a pioneering approach leveraging the available network of real-time monitoring stations and advanced machine learning algorithms that can accurately simulate spatial–temporal problems. The Spatio-Temporal Attention Gated Recurrent Unit (STA-GRU) model is renowned for its computational efficacy in forecasting streamflow events with a forecast horizon of 7 days. The novel integration of the groundwater level, precipitation, and river discharge as predictive variables offers a holistic view of the hydrological cycle, enhancing the model’s accuracy. Our findings reveal that for a 7-day forecasting period, the STA-GRU model demonstrates superior performance, with a notable improvement in mean absolute percentage error (MAPE) values and R-square (R2) alongside reductions in the root mean squared error (RMSE) and mean absolute error (MAE) metrics, underscoring the model’s generalizability and reliability. Comparative analysis with seven conventional deep learning models, including the Long Short-Term Memory (LSTM), the Convolutional Neural Network LSTM (CNNLSTM), the Convolutional LSTM (ConvLSTM), the Spatio-Temporal Attention LSTM (STA-LSTM), the Gated Recurrent Unit (GRU), the Convolutional Neural Network GRU (CNNGRU), and the STA-GRU, confirms the superior predictive power of the STA-LSTM and STA-GRU models when faced with long-term prediction. This research marks a significant shift towards an integrated network of real-time monitoring stations with advanced deep-learning algorithms for streamflow forecasting, emphasizing the importance of spatially and temporally encompassing streamflow variability within an urban watershed’s stream network.

Optimizing green supply chain circular economy in smart cities with integrated machine learning technology

This paper explores methodologies to enhance the integration of a green supply chain circular economy within smart cities by incorporating machine learning technology. To refine the precision and effectiveness of the prediction model, the gravitational algorithm is introduced to optimize parameter selection in the support vector machine model. A nationwide prediction model for green supply chain economic development efficiency is meticulously constructed by leveraging public economic, environmental, and demographic data. A comprehensive empirical analysis follows, revealing a noteworthy reduction in mean squared error and root mean squared error with increasing iterations, reaching a minimum of 0.007 and 0.103, respectively—figures that are the lowest among all considered machine learning models. Moreover, the mean absolute percentage error value is remarkably low at 0.0923. The data illustrate a gradual decline in average prediction error and standard deviation throughout the model optimization process, indicative of both model convergence and heightened prediction accuracy. These results underscore the significant potential of machine learning technology in optimizing supply chain and circular economy management. The paper provides valuable insights for decision-makers and researchers navigating the landscape of sustainable development.

Modeling the Mechanical Properties of Root–Substrate Interaction with a Transplanter Using Artificial Neural Networks

The mechanical properties of a plug seedling substrate determine whether it will crush during the transplantation, thereby affecting the integrity of the root system and the survival rate of transplanted seedlings. In this study, we measured eight morphological parameters of pepper seedlings using machine vision and physical methods, and the corresponding substrate mechanical parameters of the plug seedlings were tested using a texture analyzer. Based on the experimental data, a BPNN framework was constructed to predict the substrate mechanical properties of plug seedlings at different growth stages. The results indicate that the BPNN with a framework of [8, 15, 15, 1] exhibits higher R2 and lower errors. The mean absolute error (MAE), mean squared error (MSE), and mean absolute percentage error (MAPE) values are 7.669, 88.842, and 9.076%, respectively, with an R2 of 0.867. The average prediction accuracy of 20 test data set is 90.472%. Finally, predictions and experimental validations were conducted on the substrate mechanical properties of seedlings grown for 47 days. The results revealed that the BPNN achieved an average prediction accuracy of 93.282%. Additionally, it exhibited faster speed and lower computational costs. This study provides a reference for the non-intrusive estimation of substrate mechanical properties in plug seedlings and the design and optimization of transplanting an end-effector.

A dynamic prediction model of landslide displacement based on VMD–SSO–LSTM approach

Addressing the limitations of existing landslide displacement prediction models in capturing the dynamic characteristics of data changes, this study introduces a novel dynamic displacement prediction model for landslides. The proposed method combines Variational Mode Decomposition (VMD) with Sparrow Search Optimization (SSO) and Long Short-Term Memory (LSTM) techniques to formulate a comprehensive VMD–SSO–LSTM model. Through the application of VMD, the method dissects cumulative displacement and rainfall data, thereby extracting distinct components such as trend, periodicity, and fluctuation components for displacement, as well as low-frequency and high-frequency components for rainfall. Furthermore, leveraging Gray Correlational Analysis, the interrelationships between the periodic component of displacement and the low-frequency component of rainfall, as well as the fluctuation component of displacement and the high-frequency component of rainfall, are established. Building upon this foundation, the SSO–LSTM model dynamically predicts the interrelated displacement components, synthesizing the predicted values of each component to generate real-time dynamic forecasts. Simulation results underscore the effectiveness of the proposed VMD–SSO–LSTM model, indicating root-mean-square error (RMSE) and mean absolute percentage error (MAPE) values of 1.2329 mm and 0.1624%, respectively, along with a goodness of fit (R2) of 0.9969. In comparison to both back propagation (BP) prediction model and LSTM prediction model, the VMD–SSO–LSTM model exhibits heightened predictive accuracy.

Simulating long-term energy consumption prediction in campus buildings through enhanced data augmentation and metaheuristic-optimized artificial intelligence

Forecasting long-term energy consumption is essential to enhance resource utilization and promote sustainability in campus buildings. This study employs a comprehensive approach, integrating artificial intelligence models, data augmentation techniques, and metaheuristic optimization algorithms to predict energy consumption one year in advance. The predictive models undergo training and validation using historical energy consumption data and weather patterns. However, predicting energy consumption a year ahead presents challenges due to instability and limited training data. To tackle this, the dataset is enriched using diverse data augmentation techniques. A metaheuristic algorithm, Jellyfish Search Optimizer (JSO), is also applied to refine the best predictive models and augmentation techniques. Results demonstrate a notable enhancement in prediction accuracy by integrating data augmentation techniques, convolutional neural network models, and metaheuristic optimization algorithms. The top-performing model, JSO-MobileNet with random noise injection, achieves a Mean Absolute Percentage Error (MAPE) value of 11.95% in forecasting energy consumption for campus buildings one year ahead. This study contributes to affirming the effectiveness of the metaheuristic optimization algorithm in fine-tuning artificial intelligence models integrated with data augmentation techniques, offering a practical approach to forecasting long-term energy consumption in campus buildings. The research outlines a systematic process for identifying the optimal predictive model, the most suitable data augmentation method, and the best set of hyperparameters.

Fusing SVR with PSO Improves E-commerce Sales Prediction with 8.98% MAPE

This study explores the integration of Support Vector Regression (SVR) with Particle Swarm Optimization (PSO) to forecast clothing product sales at Nara Gallery Collection Boutique, addressing the challenge of achieving high forecast accuracy in e-commerce. Through literature review, direct observation, and interviews with a textile SME owner, SVR parameters are optimized using PSO. Results indicate a Mean Absolute Percentage Error (MAPE) value of 8.98% with optimized parameters (C = 34.3642, ε = 0.0110, σ = 0.3677, cLR = 0.1062, λ = 0.0117), enhancing decision-making in inventory management and strategic planning for e-commerce businesses. This research highlights the potential of integrating SVR with PSO for accurate sales forecasting and suggests avenues for further exploration in alternative forecasting methods and optimization techniques. Highlight: Enhanced Forecasting Accuracy: SVR and PSO integration improves e-commerce sales predictions. Parameter Optimization: PSO optimizes SVR parameters, reducing Mean Absolute Percentage Error. Strategic Inventory Management: Accurate forecasts aid in effective e-commerce inventory control. Keywoard: Support Vector Regression, Particle Swarm Optimization, Sales Forecasting, E-commerce, Inventory Management

Pemodelan Data Time Series Menggunakan Pendekatan Regresi Polinomial Lokal Pada Data Harga Saham MDKA

<p class="AbstractEnglish">Investment is an important way to manage finances for profit. One of the most popular investments in Indonesia is buying and selling shares. In addition to getting profits, they also have risks. Therefore, analyzing stock prices before buying and selling is an important key in stock investing. Investors should buy stocks at a low price and sell them at a high price. One of the methods used is parametric regression analysis, but it has assumptions that must be met. A more flexible alternative is local polynomial regression without any particular assumptions. PT Merdeka Copper Gold Tbk with MDKA stock code is a company engaged in the mining and industrialization of gold, silver, and other associated minerals. The study of modeling the lowest daily price of MDKA shares using local polynomial regression showed excellent results. The high coefficient of determination exceeding 67% on the in-sample data indicates strong model performance, and the Mean Absolute Percentage Error (MAPE) value on the out-of-sample data is less than 10%, ensuring excellent model accuracy.</p><p class="AbstractEnglish"><strong>Keywords: </strong>local polynomial regression; MDKA shares; time series</p>

Thermally modified nanocrystalline snail shell adsorbent for methylene blue sequestration: equilibrium, kinetic, thermodynamic, artificial intelligence, and DFT studies.

In recent years, the quest for an efficient and sustainable adsorbent material that can effectively remove harmful and hazardous dyes from industrial effluent has become more intense. The goal is to explore the capability of thermally modified nanocrystalline snail shells (TMNSS) as a new biosorbent for removing methylene blue (MB) dye from contaminated wastewater. TMNSS was employed in batch adsorption experiments to remove MB dye from its solutions, taking into account various adsorption parameters such as contact time, temperature, pH, adsorbent dosage, and initial concentration. SEM, EDS, XRD, and FTIR were used to characterize the adsorbent. The study further developed and adopted adaptive neuro-fuzzy inference system (ANFIS) and density functional theory (DFT) studies to holistically examine the adsorption process of MB onto the adsorbent. EDX and FTIR confirm the formation of CaO with a sharp peak at 547 cm-1, and C-O and O-H are present, as well. SEM and XRD show an irregularly shaped highly crystalline nanosized (65 ± 2.81 nm) particle with a lattice parameter value of 8.611617 Å. The adsorption efficiency of 96.48 ± 0.58% was recorded with a pH of 3.0 and an adsorbent dose of 10 mg at 30 °C. The findings from the study fit nicely onto Freundlich isotherms, with Qm = 31.7853 mg g-1 and R2 = 0.9985. Pseudo-second-order kinetics recorded the least error value of 0.8792 and R2 = 0.9868, thus indicating chemisorption and multilayer adsorption processes. The exothermic and spontaneous nature of the adsorption process are demonstrated by ΔH° and ΔG°. The performance of the ANFIS-based prediction of removal rate, which was demonstrated by a root mean square error (RMSE) value of 2.2077, mean absolute deviation (MAD) value of 1.1429, mean absolute error (MAE) value of 1.8786, and mean absolute percentage error (MAPE) value of 2.0178, revealed that the ANFIS model predictions and experimental findings are in good agreement. More so, DFT provides insights into the molecular interactions between MB and the adsorbent surface, with a calculated adsorbate-adsorbent binding affinity value of -1.3 kcal mol-1, thus confirming the ability of TMNSS for MB sequestration. The findings of this study highlight the promising potential of thermally modified nanocrystalline snail shells as sustainable and efficient adsorbents for MB sequestration.

Application of deep learning model incorporating domain knowledge in international migration forecasting

PurposeForecasting population movement trends is crucial for implementing effective policies to regulate labor force growth and understand demographic changes. Combining migration theory expertise and neural network technology can bring a fresh perspective to international migration forecasting research.Design/methodology/approachThis study proposes a conditional generative adversarial neural network model incorporating the migration knowledge – conditional generative adversarial network (MK-CGAN). By using the migration knowledge to design the parameters, MK-CGAN can effectively address the limited data problem, thereby enhancing the accuracy of migration forecasts.FindingsThe model was tested by forecasting migration flows between different countries and had good generalizability and validity. The results are robust as the proposed solutions can achieve lesser mean absolute error, mean squared error, root mean square error, mean absolute percentage error and R2 values, reaching 0.9855 compared to long short-term memory (LSTM), gated recurrent unit, generative adversarial network (GAN) and the traditional gravity model.Originality/valueThis study is significant because it demonstrates a highly effective technique for predicting international migration using conditional GANs. By incorporating migration knowledge into our models, we can achieve prediction accuracy, gaining valuable insights into the differences between various model characteristics. We used SHapley Additive exPlanations to enhance our understanding of these differences and provide clear and concise explanations for our model predictions. The results demonstrated the theoretical significance and practical value of the MK-CGAN model in predicting international migration.

Forecasting the power generation at renewable power plants in Sri Lanka using regression trees

This paper presents the application of regression trees as a versatile alternative to other machine learning and statistical modelling techniques to forecast the power generation at five renewable power plants: one large hydropower plant, two mini hydropower plants, and two wind farms in Sri Lanka. The prediction models for each power station were developed by varying the depth of the regression tree. The regression tree model with the lowest depth that forecasts the output (power) in terms of all the predictor variables was selected for each power station and the accuracy of the models was evaluated by means of the Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R2). According to the degree of the above performance indicators, i.e. very low values of MAE, MAPE, and RMSE supplemented by R2 of 0.95 or more, the regression tree method proved to be a convenient forecasting technique to predict the power generation at both hydro and wind power plants. Further, it could be found that a good correlation between the input and output variables paves the way for a smaller depth in the regression tree. Moreover, regression trees presented here could accurately identify the relationship between the power generated and the most influential weather factors, without being affected by potential outliers or missing values while managing collinearity too. Extension of this study would enable to generalize the prediction of renewable power generation based on the regression tree method, leading towards minimizing the use of fossil fuel.

Short-Term Electrical Energy Demand Forecasting Using Fuzzy Logic Technique

Minimization of electrical energy wastage and provision of its regular supply make electrical load forecasting an important aspect of the power infrastructure. An accurate load forecasting is crucial for the reduction of the cost of electrical energy generation and spinning reserve capacity. Therefore, in this study, fuzzy logic (FL) technique was employed for the projection of electrical energy demand on short-term basis. The FL model was trained using the six months hourly load and temperature data respectively obtained from 132/33 kV Ikeja West Transmission Station, Ayobo and Nigerian Meteorological Agency, Oshodi, Lagos State, Nigeria. Triangular and trapezoidal membership functions (MFs) were used in the training of the model with Mamdani fuzzy inference system. The time, load and temperature inputs were fuzzified into six, four and three MFs respectively while the fuzzification process used 25 fuzzy rule bases. The centroid method of defuzzification was used to change the results into readable values. The adequacy of the FL model was determined using five metrics including mean square error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), chi square (χ2) and F- test. The obtained results revealed that the FL model developed excelled in all the five tests of adequacy considered with MSE, MAE, MAPE, χ2 and F-test values of 4.17, 6.74, 11.51%, 7.93 and 1.27 respectively and hence, performed satisfactorily. This work established that the fuzzy logic approach is appropriate for electrical load projection on short-term basis.

Modeling and Predicting Passenger Load Factor in Air Transportation: A Deep Assessment Methodology with Fractional Calculus Approach Utilizing Reservation Data

This study addresses the challenge of predicting the passenger load factor (PLF) in air transportation to optimize capacity management and revenue maximization. Leveraging historical reservation data from 19 Turkish Airlines market routes and sample flights, we propose a novel approach combining deep assessment methodology (DAM) with fractional calculus theory. By modeling the relationship between PLF and the number of days remaining until a flight, our method yields minimal errors compared to traditional techniques. Through a continuous curve constructed using the least-squares approach, we enable the anticipation of future flight values. Our analysis demonstrates that the DAM model with a first-order derivative outperforms linear techniques and the Fractional Model-3 in both modeling capabilities and prediction accuracy. The proposed approach offers a data-driven solution for efficiently managing air transport capacity, with implications for revenue optimization. Specifically, our modeling findings indicate that the DAM wd model improves prediction accuracy by approximately 0.67 times compared to the DAM model, surpassing the fractional model and regression analysis. For the DAM wd modeling method, the lowest average mean absolute percentage error (AMAPE) value achieved is 0.571, showcasing its effectiveness in forecasting flight outcomes.

A Stochastic Regression and Sentiment Analysis-Based Approach for Forecasting Trends in the Stock Market

Stochastic regression problems especially applied to time series forecasting problems often encounter the challenge of volatility and unpredictable seasonality in datasets. One such application happens to forecasting the movement of stock markets globally. Stock data across the world exhibits an intrinsic baseline noise, which often can’t be correlated to previous temporal patterns. Rather, such divergences are an effect of multiple non-numeric variables which govern stock movement such as political scenarios, trade wars, imminent economic waxing and waning trends to name a few. However, it is essential to incorporate these factors while training a model so as to design a strongly sentient and anticipatory regression algorithm which is both pervasive and robust, encompassing as many numeric and non-numeric factors as possible. While conventional machine learning and deep learning approaches tend to leverage tested model architectures, they often miss out on the optimization of both training data and training method to yield potentially high forecasting accuracy. The paper combines stochastic regression in terms of momentum based training and data optimization which is shown to exhibit considerable lower forecasting error compared to existing approaches. To encompass a wider feature space, sentiment analysis has been incorporated to correlate stock movements with public opinions. The proposed approach has been tested on a multitude of benchmark datasets, to validate the performance of the approach. The mean absolute percentage error (MAPE) and regression values have been selected as primary metrics for the performance evaluation. The proposed approach attains a mean MAPE value of 3.22%. The analysis of the MAPE and forecasting accuracy w.r.t. existing benchmark approaches proves the improved forecasting performance of the proposed approach over a period of 300 days.