Revolutionizing Retail: A Hybrid Machine Learning Approach for Precision Demand Forecasting and Strategic Decision-Making in Global Commerce

Journal of Computer Science and Technology Studies, Год журнала: 2024, Номер 6(1), С. 33 - 39

Опубликована: Янв. 2, 2024

A thorough comparison of several machine learning methods is provided in this paper, including gradient boosting, AdaBoost, Random Forest (RF), XGBoost, Artificial Neural Network (ANN), and a unique hybrid framework (RF-XGBoost-LR). The assessment investigates their efficacy real-time sales data analysis using key performance metrics like Mean Absolute Error (MAE), Squared (MSE), R2 score. study introduces the model RF-XGBoost-LR, leveraging both bagging boosting methodologies to address limitations individual models. Notably, XGBoost are scrutinized for strengths weaknesses, with strategically combining merits. Results demonstrate superior proposed terms accuracy robustness, showcasing potential applications supply chain studies demand forecasting. findings highlight significance industry-specific customization emphasize improved decision-making, marketing strategies, inventory management, customer satisfaction through precise

Язык: Английский

---

Deep Learning in Stock Market Forecasting: Comparative Analysis of Neural Network Architectures Across NSE and NYSE

Journal of Computer Science and Technology Studies, Год журнала: 2024, Номер 6(1), С. 68 - 75

Опубликована: Янв. 13, 2024

This research explores the application of four deep learning architectures—Multilayer Perceptron (MLP), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Convolutional (CNN)—in predicting stock prices using historical data. Focusing on day-wise closing from National Stock Exchange (NSE) India New York (NYSE), study trains neural network NSE data tests it both NYSE stocks. Surprisingly, CNN model outperforms others, successfully despite being trained Comparative analysis against ARIMA underscores superior performance networks, emphasizing their potential in forecasting market trends. sheds light shared underlying dynamics between distinct markets demonstrates efficacy architectures price prediction.

Язык: Английский

---

Advanced Cybercrime Detection: A Comprehensive Study on Supervised and Unsupervised Machine Learning Approaches Using Real-world Datasets

Journal of Computer Science and Technology Studies, Год журнала: 2024, Номер 6(1), С. 40 - 48

Опубликована: Янв. 2, 2024

In the ever-evolving field of cybersecurity, sophisticated methods—which combine supervised and unsupervised approaches—are used to tackle cybercrime. Strong tools include Support Vector Machines (SVM) K-Nearest Neighbors (KNN), while well-known methods K-means clustering model. These techniques are on publicly available StatLine dataset from CBS, which is a large that includes individual attributes one thousand crime victims. Performance analysis shows remarkable 91% accuracy SVM in classification by examining differences between training testing data. (KNN) models quite good arena; their detecting criminal activity impressive, at 79.56%. assessment metrics, such as False Positive (FP), True Negative (TN), (FN), (TP), Alarm Rate (FAR), Detection (DR), Accuracy (ACC), Recall, Precision, Specificity, Sensitivity, Fowlkes–Mallow's scores, provide comprehensive assessment.

Язык: Английский

---

Harmonizing Macro-Financial Factors and Twitter Sentiment Analysis in Forecasting Stock Market Trends

Journal of Computer Science and Technology Studies, Год журнала: 2024, Номер 6(1), С. 58 - 67

Опубликована: Янв. 7, 2024

The surge in generative artificial intelligence technologies, exemplified by systems such as ChatGPT, has sparked widespread interest and discourse prominently observed on social media platforms like Twitter. This paper delves into the inquiry of whether sentiment expressed tweets discussing advancements AI can forecast day-to-day fluctuations stock prices associated companies. Our investigation involves analysis containing hashtags related to ChatGPT within timeframe December 2022 March 2023. Leveraging natural language processing techniques, we extract features, including positive/negative scores, from collected tweets. A range classifier machine learning models, encompassing gradient boosting, decision trees random forests, are employed train tweet sentiments features for prediction price movements among key companies, Microsoft OpenAI. These models undergo training testing phases utilizing an empirical dataset gathered during stipulated timeframe. preliminary findings reveal intriguing indications suggesting a plausible correlation between public reflected Twitter discussions surrounding subsequent impact market valuation trading activities concerning pertinent gauged through prices. study aims bullish or bearish trends leveraging derived extensive comprising 500,000 In conjunction with this Twitter, incorporate control variables macroeconomic indicators, uncertainty index data several prominent

Язык: Английский

---

Parkinson's Disease Detection through Vocal Biomarkers and Advanced Machine Learning Algorithms

Journal of Computer Science and Technology Studies, Год журнала: 2023, Номер 5(4), С. 142 - 149

Опубликована: Дек. 2, 2023

Parkinson's disease (PD) is a prevalent neurodegenerative disorder known for its impact on motor neurons, causing symptoms like tremors, stiffness, and gait difficulties. This study explores the potential of vocal feature alterations in PD patients as means early prediction. research aims to predict onset disease. Utilizing variety advanced machine-learning algorithms, including XGBoost, LightGBM, Bagging, AdaBoost, Support Vector Machine, among others, evaluates predictive performance these models using metrics such accuracy, area under curve (AUC), sensitivity, specificity. The findings this comprehensive analysis highlight LightGBM most effective model, achieving an impressive accuracy rate 96% alongside matching AUC 96%. exhibited remarkable sensitivity 100% specificity 94.43%, surpassing other machine learning algorithms scores. Given complexities challenges diagnosis, underscores significance leveraging biomarkers coupled with techniques precise timely detection.

Язык: Английский

---

Unleashing Deep Learning: Transforming E-commerce Profit Prediction with CNNs

Journal of Business and Management Studies, Год журнала: 2024, Номер 6(2), С. 126 - 131

Опубликована: Апрель 11, 2024

This research examines the potential of Convolutional Neural Networks (CNNs), including VGG16, ResNet50, and InceptionV3, in predicting ecommerce profits. Emphasizing importance high-quality datasets, study showcases superior performance CNN models over traditional algorithms, particularly noting a notable accuracy rate 92.55% with (VGG16). These results highlight deep learning's capability to extract actionable insights from complex data, offering significant opportunities for revenue optimization operational efficiency improvement. The conclusion underscores need investment infrastructure expertise successful integration, alongside ethical privacy considerations. contributes valuable discourse on learning ecommerce, guidance businesses navigating competitive global market landscape.

Язык: Английский

---

Comparing Machine Learning Techniques for Detecting Chronic Kidney Disease in Early Stage

Journal of Computer Science and Technology Studies, Год журнала: 2024, Номер 6(1), С. 20 - 32

Опубликована: Янв. 2, 2024

In medical care, side effect trial and error processes are utilized for the discovery of hidden reasons ailments determination conditions. our exploration, we used a crossbreed strategy to refine optimal model, improving Pearson relationship highlight choice purposes. The underlying stage included ideal models through careful survey current writing. Hence, proposed half-and-half model incorporated blend these models. base classifiers XGBoost, Arbitrary Woods, Strategic Relapse, AdaBoost, Crossover classifiers, while Meta classifier was Irregular Timberland classifier. essential target this examination evaluate best AI grouping techniques decide concerning accuracy. This approach resolved issue overfitting accomplished most elevated level exactness. focal point assessment precision, introduced far-reaching significant writing in even configuration. To carry out methodology, four top-performing fostered another named "half half," utilizing UCI Persistent Kidney Disappointment dataset prescient experiment, found that XGBoost gains almost 94% accuracy, random forest 93% Logistic Regression about 90% AdaBoost 91% new hybrid highest 95% performance Hybrid is on equivalent dataset. Various noticeable have been foresee event persistent kidney disappointment (CKF). These incorporate Naïve Bayes, Random Forest, Decision Tree, Support Vector Machine, K-nearest neighbor, LDA (Linear Discriminant Analysis), GB (Gradient Boosting), neural networks. examination, explicitly Regression, with highlights analyze their accuracy scores.

Язык: Английский

---

Improving Cardiovascular Disease Prediction Through Comparative Analysis of Machine Learning Models: A Case Study on Myocardial Infarction

Опубликована: Ноя. 14, 2023

Cardiovascular disease remains a leading cause of mortality in the contemporary world. Its association with smoking, elevated blood pressure, and cholesterol levels underscores significance these risk factors. This study addresses challenge predicting myocardial illness, formidable task medical research. Accurate predictions are pivotal for refining healthcare strategies. investigation conducts comparative analysis six distinct machine learning models: Logistic Regression, Support Vector Machine, Decision Tree, Bagging, XGBoost, LightGBM. The attained outcomes exhibit promise, accuracy rates as follows: Regression (81.00%), Machine (75.01%), XGBoost (92.72%), LightGBM (90.60%), Tree (82.30%), Bagging (83.01%). Notably, emerges top-performing model. These findings underscore its potential to enhance predictive precision coronary infarction. As prevalence cardiovascular factors persists, incorporating advanced techniques holds refine proactive interventions.

Язык: Английский

---

Optimizing E-Commerce Profits: A Comprehensive Machine Learning Framework for Dynamic Pricing and Predicting Online Purchases

Journal of Computer Science and Technology Studies, Год журнала: 2023, Номер 5(4), С. 186 - 193

Опубликована: Дек. 15, 2023

In the online realm, pricing transparency is crucial in influencing consumer decisions and driving purchases. While dynamic not a novel concept widely employed to boost sales profit margins, its significance for retailers substantial. The current study an outcome of ongoing project that aims construct comprehensive framework deploy effective techniques, leveraging robust machine learning algorithms. objective optimize strategy on e-commerce platforms, emphasizing importance selecting right purchase price rather than merely offering cheapest option. Although primarily targets inventory-led companies, model's applicability can be extended marketplaces operate without maintaining inventories. endeavors forecast based adaptive or strategies individual products by integrating statistical models. Various data sources capturing visit attributes, visitor details, history, web data, contextual insights form foundation this framework. Notably, specifically emphasizes predicting purchases within customer segments focusing buyers. logical progression research involves personalization prediction, with future extensions planned once outcomes are presented. solution landscape encompasses mining, big technologies, implementation

Язык: Английский

---

Improving Cardiovascular Disease Prediction through Comparative Analysis of Machine Learning Models

Journal of Computer Science and Technology Studies, Год журнала: 2024, Номер 6(2), С. 62 - 70

Опубликована: Апрель 20, 2024

Cardiovascular diseases, including myocardial infarction, present significant challenges in modern healthcare, necessitating accurate prediction models for early intervention. This study explores the efficacy of machine learning algorithms predicting leveraging a dataset comprising various clinical attributes sourced from patients with heart failure. Six models, Logistic Regression, Support Vector Machine, XGBoost, LightGBM, Decision Tree, and Bagging, are evaluated based on key performance metrics such as accuracy, precision, recall, F1 Score, AUC. The results reveal XGBoost top performer, achieving an accuracy 94.80% AUC 90.0%. LightGBM closely follows 92.50% 92.00%. Regression emerges reliable option 85.0%. underscores potential enhancing infarction prediction, offering valuable insights decision-making healthcare intervention strategies.

Язык: Английский

---