Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Noise to Insights: Enhancing Supply Chain Decision Support through AI-Based Survey Integrity Analytics

Bhubalan Mani

TL;DR

The paper tackles unreliable survey data in supply-chain AI adoption assessments and introduces a lightweight AI-based pipeline that fuses logic-rule filtering, NLP-based textual coherence scoring, and supervised classification. On a real-world dataset of 99 responses, Random Forest and XGBoost achieved up to 92% accuracy, with perfect precision on the fake class but limited recall due to class imbalance. This approach enhances data integrity for product launches and technology adoption in supply chains, enabling more reliable, data-driven decisions and scalable deployment. It also outlines practical pathways for real-time integration, larger datasets, and human-in-the-loop improvements to advance enterprise survey workflows.

Abstract

The reliability of survey data is crucial in supply chain decision-making, particularly when evaluating readiness for AI-driven tools such as safety stock optimization systems. However, surveys often attract low-effort or fake responses that degrade the accuracy of derived insights. This study proposes a lightweight AI-based framework for filtering unreliable survey inputs using a supervised machine learning approach. In this expanded study, a larger dataset of 99 industry responses was collected, with manual labeling to identify fake responses based on logical inconsistencies and response patterns. After preprocessing and label encoding, both Random Forest and baseline models (Logistic Regression, XGBoost) were trained to distinguish genuine from fake responses. The best-performing model achieved an 92.0% accuracy rate, demonstrating improved detection compared to the pilot study. Despite limitations, the results highlight the viability of integrating AI into survey pipelines and provide a scalable solution for improving data integrity in supply chain research, especially during product launch and technology adoption phases.

From Noise to Insights: Enhancing Supply Chain Decision Support through AI-Based Survey Integrity Analytics

TL;DR

The paper tackles unreliable survey data in supply-chain AI adoption assessments and introduces a lightweight AI-based pipeline that fuses logic-rule filtering, NLP-based textual coherence scoring, and supervised classification. On a real-world dataset of 99 responses, Random Forest and XGBoost achieved up to 92% accuracy, with perfect precision on the fake class but limited recall due to class imbalance. This approach enhances data integrity for product launches and technology adoption in supply chains, enabling more reliable, data-driven decisions and scalable deployment. It also outlines practical pathways for real-time integration, larger datasets, and human-in-the-loop improvements to advance enterprise survey workflows.

Abstract

The reliability of survey data is crucial in supply chain decision-making, particularly when evaluating readiness for AI-driven tools such as safety stock optimization systems. However, surveys often attract low-effort or fake responses that degrade the accuracy of derived insights. This study proposes a lightweight AI-based framework for filtering unreliable survey inputs using a supervised machine learning approach. In this expanded study, a larger dataset of 99 industry responses was collected, with manual labeling to identify fake responses based on logical inconsistencies and response patterns. After preprocessing and label encoding, both Random Forest and baseline models (Logistic Regression, XGBoost) were trained to distinguish genuine from fake responses. The best-performing model achieved an 92.0% accuracy rate, demonstrating improved detection compared to the pilot study. Despite limitations, the results highlight the viability of integrating AI into survey pipelines and provide a scalable solution for improving data integrity in supply chain research, especially during product launch and technology adoption phases.
Paper Structure (23 sections, 6 figures, 1 table)

This paper contains 23 sections, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Dataset Overview
  5. Data Preprocessing
  6. Logic-Based Filtering
  7. NLP-Based Scoring (Textual Coherence)
  8. Machine Learning Classification
  9. Visualization and Interpretation
  10. SYSTEM ARCHITECTURE
  11. Survey Input Module
  12. Data Cleaning and Preprocessing Module
  13. AI Logic Engine
  14. Dashboard and Analytics Module
  15. Results
  16. ...and 8 more sections

Figures (6)

  • Figure 1: Confusion Matrix - Random Forest.
  • Figure 2: Confusion Matrix - Logistic Regression.
  • Figure 3: Confusion Matrix - XGBoost.
  • Figure 4: Feature Importance.
  • Figure 5: NLP Score Plots.
  • ...and 1 more figures