Subtopic Deep Dive

← Information Systems and Technology Applications

Machine Learning in Information Systems
Research Guide

What is Machine Learning in Information Systems?

Machine Learning in Information Systems applies supervised learning, neural networks, collaborative filtering, and NLP techniques to enterprise data for content classification, recommendation systems, anomaly detection, and process automation.

This subtopic covers ML integration into business information systems for tasks like personalized recommendations and authorship identification. Key works include collaborative filtering systems (Lytvyn et al., 2019, 41 citations) and neural network-based content distribution (Lytvyn et al., 2019, 34 citations). Over 10 recent papers from 2019-2023 explore these applications, with 300+ total citations.

Curated Papers

Key Challenges

Why It Matters

ML enhances enterprise recommendation systems, improving user engagement in commercial content distribution (Lytvyn et al., 2019). Neural networks model interactions in complex IT projects, predicting outcomes for distributed information systems (Morozov et al., 2020). Hopfield networks analyze recruitment data for better hiring decisions (Jamaludin et al., 2020), while NLP identifies authorship in journalistic texts (Lupei et al., 2020), automating business intelligence from unstructured data.

Key Research Challenges

Scalability in Enterprise Data

Processing large-scale enterprise data with neural networks demands high computational resources, as seen in IT project modeling (Morozov et al., 2020). Balancing model complexity and performance remains difficult. Privacy-preserving federated learning is underexplored in business contexts.

Personalization Accuracy

Collaborative filtering struggles with cold-start problems for new users in recommendation systems (Lytvyn et al., 2019). Integrating user needs with ML requires hybrid approaches. Evaluation metrics often overlook long-term engagement.

NLP for Non-English Texts

Authorship identification in Ukrainian journalistic texts using neural networks faces language-specific preprocessing challenges (Lupei et al., 2020). Limited training data hampers generalization. Cross-lingual transfer learning is needed for enterprise applications.

Essential Papers

E-Learning Based on Cloud Computing

Wei Wu, Anastasiia Plakhtii · 2021 · International Journal of Emerging Technologies in Learning (iJET) · 70 citations

Modern technological paradigms of learning give educators an ability to support the development of highly professional human resources. For this reason, teachers of higher educational institutions ...

Employee Training in an Intelligent Factory Using Virtual Reality

Przemysław Zawadzki, Krzysztof Żywicki, Paweł Buń et al. · 2020 · IEEE Access · 49 citations

The article presents the results of research on the impact of virtual reality on the effectiveness of training employees performing production tasks. The research was carried out in the Smart Facto...

Unlocking the power of synergy: the joint force of cloud technologies and augmented reality in education

Stamatios Papadakis, Arnold Kiv, Hennadiy Kravtsov et al. · 2023 · 45 citations

This is an introductory text to a collection of selected papers from the 10th Workshop on Cloud Technologies in Education (CTE 2021) and 5th International Workshop on Augmented Reality in Education...

Design of a recommendation system based on collaborative filtering and machine learning considering personal needs of the user

Vasyl Lytvyn, Victoria Vysotska, Viktor Shatskykh et al. · 2019 · Eastern-European Journal of Enterprise Technologies · 41 citations

&lt;p&gt;The paper reports a study into recommendation algorithms and determination of their advantages and disadvantages. The method for developing recommendations based on collaborative f...

Cloud services application ways for preparation of future PhD

Anna Іatsyshyn, Валерія Ковач, Yevhen Romanenko et al. · 2019 · CTE Workshop Proceedings · 39 citations

Currently, it is important in Ukraine to harmonize cloud technologies application with European and world scientific initiatives. Need to modernize preparation of future PhDs is caused by challenge...

THE METHOD OF INTERACTION MODELING ON BASIS OF DEEP LEARNING THE NEURAL NETWORKS IN COMPLEX IT-PROJECTS

В. В. Морозов, Olena Kalnichenko, Olga Mezentseva · 2020 · International Journal of Computing · 38 citations

In this paper, we propose a method for using neural networks to model impacts on the parameters of complex IT projects for the creation of distributed information systems. The method allows predict...

Energy Based Logic Mining Analysis with Hopfield Neural Network for Recruitment Evaluation

Siti Zulaikha Mohd Jamaludin, Mohd Shareduwan Mohd Kasihmuddin, Ahmad Izani Md. Ismail et al. · 2020 · Entropy · 36 citations

An effective recruitment evaluation plays an important role in the success of companies, industries and institutions. In order to obtain insight on the relationship between factors contributing to ...

Reading Guide

Foundational Papers

Start with 'Digital asset management - a closer look at the literature' (Frey et al., 2005) for early content management context, then 'ECMs and Institutional Repositories' (Wolski et al., 2013) for enterprise content systems foundational to ML integration.

Recent Advances

Study Lytvyn et al. (2019, 41 citations) for collaborative filtering, Morozov et al. (2020, 38 citations) for deep learning in IT projects, and Jamaludin et al. (2020, 36 citations) for Hopfield networks in recruitment.

Core Methods

Core methods are collaborative filtering (Lytvyn et al., 2019), Hopfield neural networks (Jamaludin et al., 2020), deep neural networks for modeling (Morozov et al., 2020), and NLP classifiers (Lupei et al., 2020).

How PapersFlow Helps You Research Machine Learning in Information Systems

Discover & Search

Research Agent uses searchPapers and exaSearch to find ML in IS papers like 'Design of a recommendation system based on collaborative filtering' (Lytvyn et al., 2019); citationGraph reveals connections to neural network modeling (Morozov et al., 2020), while findSimilarPapers uncovers related works on Hopfield networks (Jamaludin et al., 2020).

Analyze & Verify

Analysis Agent employs readPaperContent on Lytvyn et al. (2019) to extract filtering algorithms, verifies claims with CoVe against citationGraph data, and runs PythonAnalysis with pandas to replicate recommendation metrics; GRADE grading assesses evidence strength for enterprise applicability.

Synthesize & Write

Synthesis Agent detects gaps in personalization techniques across Lytvyn papers, flags contradictions in neural network scalability; Writing Agent uses latexEditText and latexSyncCitations to draft IS-ML reviews, latexCompile for publication-ready docs, exportMermaid for model flowcharts.

Use Cases

"Replicate Hopfield network recruitment analysis from Jamaludin et al. 2020"

Research Agent → searchPapers → Analysis Agent → readPaperContent + runPythonAnalysis (NumPy/pandas to recompute energy-based logic mining) → matplotlib plots of recruitment evaluation metrics.

"Write LaTeX review of collaborative filtering in enterprise recommendations"

Research Agent → citationGraph on Lytvyn 2019 → Synthesis → gap detection → Writing Agent → latexEditText + latexSyncCitations + latexCompile → PDF with diagram via exportMermaid.

"Find GitHub repos for neural network IT project modeling code"

Research Agent → searchPapers (Morozov 2020) → Code Discovery → paperExtractUrls → paperFindGithubRepo → githubRepoInspect → verified implementation of deep learning interaction models.

Automated Workflows

Deep Research workflow scans 50+ ML-IS papers via searchPapers, structures reports on recommendation trends with GRADE grading. DeepScan applies 7-step analysis with CoVe checkpoints to verify neural network claims in Morozov et al. (2020). Theorizer generates hypotheses on hybrid filtering from Lytvyn et al. papers.

Try Doxa for Machine Learning in Information Systems Research

Frequently Asked Questions

What defines Machine Learning in Information Systems?

It applies ML techniques like collaborative filtering and neural networks to enterprise tasks such as recommendations and anomaly detection (Lytvyn et al., 2019; Morozov et al., 2020).

What are key methods used?

Methods include collaborative filtering (Lytvyn et al., 2019), Hopfield neural networks (Jamaludin et al., 2020), and deep learning for interaction modeling (Morozov et al., 2020).

What are prominent papers?

Top papers are Lytvyn et al. (2019, 41 citations) on recommendations, Morozov et al. (2020, 38 citations) on IT project neural networks, and Lupei et al. (2020, 33 citations) on NLP authorship.

What open problems exist?

Challenges include scalability for enterprise data, cold-start in recommendations, and NLP for low-resource languages like Ukrainian (Lupei et al., 2020).