Focus and Scopes

Focus
The International Journal of Data Science (IJoDS) champions the advancement of data science by publishing high-quality, original research that explores theoretical advancements, empirical methodologies, and diverse real-world applications. Our core mission is to illuminate the entire data lifecycle while placing a significant emphasis on solving domain-specific challenges through advanced computational techniques. IJoDS serves as a premier international platform for researchers to disseminate innovative work, with a special focus on applied machine learning, predictive modeling, computational benchmarking, and the integration of data science into multiple sectors. We encourage studies that not only propose novel models but also critically evaluate their performance against classical approaches in modern scientific computing environments.

Scope

The scope of IJoDS is broad, multidisciplinary, and highly applied, welcoming contributions that explore and innovate across a wide spectrum of data science. The journal seeks to cover key methodologies, diverse application domains, and specific problem-solving frameworks. The specific areas of interest include:

Key Methodologies and Techniques:
  • Machine Learning & Deep Learning: Application of supervised and unsupervised learning, including traditional models (e.g., Random Forest, SVM, Naive Bayes, XGBoost) and advanced neural networks (e.g., CNN, RNN, LSTM, MLP, and Spatio-Temporal Graph Convolutional Networks).
  • Feature Engineering & Optimization: Dimensionality reduction and feature selection techniques, including Principal Component Analysis (PCA), Recursive Feature Elimination (RFE), and Evolutionary/Genetic Algorithms.
  • Natural Language Processing (NLP): Text mining, sentiment analysis, sarcasm detection, TF-IDF representations, and the integration of Large Language Models (LLMs) and APIs for document parsing.
  • Statistical Analysis & Forecasting: Time series analysis, non-parametric regression modeling (regression splines, smoothing splines), and smoothing methods (Double Exponential Smoothing).
  • Big Data Analytics: Distributed computing frameworks, Hadoop ecosystems, and MapReduce for processing large-scale network and social media data.
  • Computational Simulation & Benchmarking: Monte Carlo simulations, algorithmic performance analysis, and programming language benchmarking (e.g., Python, Julia, R).
  • Bibliometric & Landscape Analysis: Systematic mapping of scientific literature and research trends using visualization tools like VOSviewer and Scopus analytics.
Key Application Domains: Unlike traditional theoretical journals, IJoDS heavily emphasizes domain-specific applications, including but not limited to:
  • Healthcare, Epidemiology & Biomedicine: Chronic disease prediction (stroke, diabetes), acute leukemia classification via gene expression, viral outbreak surveillance (e.g., Lassa fever), and culturally aligned AI diagnostic systems.
  • Finance & Economics: Loan interest rate forecasting, European options pricing, and analyzing AI adoption patterns in the banking sector.
  • Social & Behavioral Sciences: Social network influential node identification, student behavior analytics, and public sentiment tracking regarding political events.
  • Cybersecurity & Information Systems: Phishing URL detection, smart attendance systems, and AI-driven Applicant Tracking Systems (ATS).
  • Agriculture, Environment, & Transportation: Crop yield prediction using artificial neural networks and drought indices, as well as spatiotemporal urban traffic forecasting.
Types of Problems Addressed: The journal publishes research that focuses on:
  • Predictive Modeling and Risk Forecasting.
  • Classification, Detection, and Categorization (e.g., disease classification, anomaly/phishing detection).
  • Comparative Evaluation of algorithms, techniques, and software tools.
  • System Development and Application Architecture.
  • Data Summarization, Geospatial Visualization, and Network Centrality Analysis.

Journal Subject Classifications (ASJC Codes)
The International Journal of Data Science primarily covers subjects within the following All Science Journal Classification (ASJC) codes:

  • 1700 General Computer Science
  • 1702 Artificial Intelligence
  • 1706 Computer Science Applications
  • 1710 Information Systems
  • 2613 Statistics and Probability