Using Machine Learning Techniques to Forecast Mehram Company's Sales: A Case Study

Journal of Business and Management Studies, Journal Year: 2024, Volume and Issue: 6(2), P. 42 - 53

Published: March 7, 2024

Sales forecasting, situated at the intersection of art and science, is critical for inspiring managers toward achieving profitable outcomes. Its precision sustains production levels capital plays a pivotal role in company's its leaders' overall success career progression. In context Mahram Food Industries, challenge arises from diverse investor perspectives impactful nature numerous variables. To address this, new sales forecasting algorithm has been introduced to enhance accuracy. The aim predict future through comprehensive approach, leveraging technical analysis, time series modeling, machine learning, neural networks, random forest techniques. research methodology integrates various advanced techniques improve Industries. Technical methods are combined create robust framework. focus on predicting period within artificial intelligence-based learning domain. study employs metrics such as Mean Absolute Deviation (MAD), MAD Percentage (MADP), Squared Error (MSE) evaluate compare performance proposed network against traditional like multiple variable regression modeling. study's results highlight superior (MAD) 28.33, outperforming (28.54) modeling (29.45). Additionally, demonstrates better (MADP) with value 10.2%, surpassing values associated (10.35%) (10.30%). further confirms network's superiority 6452 compared 6472 7865 respectively. conclusion, showcases effectiveness integrating techniques, particularly network, enhancing accuracy combining forest, valuable strategy sales. evidenced by lower MAD, MADP, MSE values, suggests potential guiding informed decision-making goal setting, hiring, budgeting, other aspects business management.

Language: Английский

---

Role of artificial intelligence in early diagnosis and treatment of infectious diseases

Infectious Diseases, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 26

Published: Nov. 14, 2024

Infectious diseases remain a global health challenge, necessitating innovative approaches for their early diagnosis and effective treatment. Artificial Intelligence (AI) has emerged as transformative force in healthcare, offering promising solutions to address this challenge. This review article provides comprehensive overview of the pivotal role AI can play treatment infectious diseases. It explores how AI-driven diagnostic tools, including machine learning algorithms, deep learning, image recognition systems, enhance accuracy efficiency disease detection surveillance. Furthermore, it delves into potential predict outbreaks, optimise strategies, personalise interventions based on individual patient data be used gear up drug discovery development (D3) process.The ethical considerations, challenges, limitations associated with integration management are also examined. By harnessing capabilities AI, healthcare systems significantly improve preparedness, responsiveness, outcomes battle against

Language: Английский

---

A Natural Language Processing–Driven Framework for Policymaking in Infrastructure Development

Journal of Construction Engineering and Management, Journal Year: 2025, Volume and Issue: 151(5)

Published: Feb. 19, 2025

Language: Английский

---

Automatic Systems of Time Series Analysis on the Basis of AutoML

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 411 - 422

Published: Jan. 1, 2025

Language: Английский

---

The Use of Artificial Intelligence in Supply Chain Project Management: Insights from German Organizations

Future of business and finance, Journal Year: 2025, Volume and Issue: unknown, P. 43 - 56

Published: Jan. 1, 2025

Language: Английский

---

The C-BA method: enhancing megaproject forecasting through the “Fifth Hand” principle

International Journal of Managing Projects in Business, Journal Year: 2025, Volume and Issue: 18(8), P. 50 - 78

Published: April 21, 2025

Purpose Current theoretical viewpoints regarding the performance trends of megaprojects endorse notion that incorporating an outside perspective during forecasting phase can be advantageous for overall progress megaproject. This paper aims to propose a novel approach, clustering-behavior analysis (C-BA), leverages unsupervised machine learning integrate as support megaproject forecasting. Design/methodology/approach Employing database 90 megaprojects, we demonstrated application C-BA. By utilizing techniques, method uncovers unforeseen patterns among past clusters them based on these and allows conducting comparison with current megaprojects. Findings The findings reveal proposed C-BA offers effective alternative supporting forecasting, aligning Fifth Hand principle. For practitioners, this would facilitate efficient benchmarking has potential serve system within organizations. Originality/value originality work lies in introducing integrates into megaproject, forecasts learning. approach aligns principle highlights artificial intelligence system, offering new avenue management. adds complex network theory by giving possibility analyzing uniqueness unpredictable nature

Language: Английский

---

A New Classification Model Using a Decision Tree Generated from Hyperplanes in Dimensional Space

Applied Artificial Intelligence, Journal Year: 2024, Volume and Issue: 38(1)

Published: Nov. 10, 2024

One of the issues addressed by machine learning, with applications in various disciplines or fields such as health sector and agricultural among others, involves data classification. For this purpose, models within supervised learning have been proposed developed that allow for classification these data. However, one implications No-Free-Lunch theorems is there no optimal general-purpose model, i.e. classifier model achieves best results all problems presented. Hence importance proposing implementing new models, evaluating their performance, comparing them other order to achieve good specific problems. This work presents a that, constructing hyperplanes from training set, generates decision tree partitions dimensional space. The was applied different XOR logical function problem, where managed solve it also Iris Dataset trees generated classify 100% accuracy test finally, Pima Indians Diabetes Database compared using value. obtained an 81.81%, achieving result same way Random Forest Classifier. show manages partition space adequately set thus competitively state-of-the-art models.

Language: Английский

---

The Evolution of Technology in Artificial Intelligence and Its Impact on Project Management

Published: Jan. 1, 2024

The rapid advancement of Artificial Intelligence (AI) has the potential for an immense impact on Project Management (PM), given ability to automate, assist, and predict project outcomes in increasingly generalizable accurate fashion. public discussion, however, is mainly concerned with possible applications AI, such as ChatGPT PM, its detrimental effects employment without a solid knowledge technological evolution. Based systematic literature review, our research explored development AI technology over past few years any trends, investigated state application developed propositions future developments based this. results indicate accelerated machine learning (ML) technologies towards deep (DL), natural language processing (NLP), computer vision (CV) multiple PM. Surprisingly, shows that most examples PM occur conventional construction industry. In general, still infancy. results, we show potentials areas which can be utilized basis practical application.

Language: Английский

---

Automating Adhesion Evaluation: The Synergy of Underwater Ndt and Artificial Intelligence in Coating Analysis

Published: Jan. 1, 2024

This study presents a novel approach for assessing coating adhesion through the integration of underwater non-destructive testing (NDT) and artificial intelligence (AI). Utilizing Lamb waves, specifically S3 mode, short-time Fourier transform (STFT) analysis was employed to enhance signal assessment accuracy. Results from experiments in adhesive delaminated regions demonstrated effectiveness waves adhesion. Traditional approaches often require specialized knowledge are time-consuming, driving need an automated, efficient solution. The proposed system employs logistic regression, statistical method well-suited binary classification tasks, differentiate between bonded conditions. operates two main stages: processing regression classification. In stage, time-domain amplitude variation graphs analyzed extract critical features: Average Amplitude Change (AAC) maximum amplitude. These features indicative coating's condition used train model. system's efficacy is report, which indicates overall accuracy 86%, with high precision recall rates both results highlight potential significantly reduce reliance on expert manual inspection, offering faster, more reliable means integrity.

Language: Английский

---

Прогнозування інцидентів під час планування спринтів у ІТ-проєктах

Scientific Bulletin of UNFU, Journal Year: 2024, Volume and Issue: 34(2), P. 78 - 86

Published: March 4, 2024

Зосереджено увагу на обґрунтуванні доцільності застосування технології машинного навчання для підвищення ефективності планування процесів, виконання яких передбачено в ітерації (Sprints) ІТ-проєкту, що реалізовують з використанням методології Scrum. Розглянуто проблеми, які виникають під час задач такого проєкту. Проаналізовано причини некоректного та шляхи можливого вирішення проблеми. Виокремлено проблему управління незапланованими у проєкті процесами визначено вплив їх появи коректність ітерацій. Проведено аналіз використання технологій прогнозування кількості незапланованих завдань впродовж майбутніх ітерацій запропоновано ці завдання трактувати як інциденти (апаратні збої). Визначено чинники, впливають виникнення процесів роботи трьох сегментах: історичні показники інцидентів, апаратне забезпечення дані мережевого навантаження. Обрано засіб – регресор екстремального градієнтного підсилення за допомогою нього проведено ймовірності роботи. основні принципи алгоритму. Описано переваги цього методу контексті досліджуваного середовища. Висвітлено особливості процедури порівняльного аналізу моделей регресії. Продемонстровано підбору даних ознак результат процесу візуалізовано результати методу. Обґрунтовано вибір робочої моделі регресії представлено прогнозування. практичне підходу. Сформовано контрольну експериментальну команди дослідження. Наведено приклад результатів ітерації. порівняльний підходів до урахуванням без них Відображено оцінено процес прийняття рішень. Доведено ефективність проєкту, реалізують перспективи розвитку подальших напрямів дослідження, галузі отриманих результатів.

---