A Singapore Government Agency Website
How to identify
Official website links end with .gov.sg
Government agencies communicate via .gov.sg websites (e.g. go.gov.sg/open). Trusted websites
Secure websites use HTTPS
Look for a lock () or https:// as an added precaution. Share sensitive information only on official, secure websites.
LogoLogoHomeAboutFAQsEventsProblem Statements
LogoLogo
Sign up here

{build} Hackathon & Incubator

Are you ready to be part of the next {build}?

Contact UsReport VulnerabilityPrivacy StatementTerms of Use
GovTech 10th AnniversaryGovTech 10th Anniversary

© 2026 Government Technology Agency of Singapore | GovTech

Projects/Data & AI
GreenAccuracy

GreenAccuracy

Improving Data Accuracy with AI

Booth DA11
Back to all projects

Green Accuracy

Team members and respective divisions:

The team comprises members from GovTech's Government Digital Transformation (GVT-GDT) group, each specializing in different business domains within NEA.

Vijaya KONDALA, David HUANG and Woon Che TAN - Integrated Environment Protection Systems and Environmental Tech (IEPET)

Mohamed TARIQ - IT Joint Ops Systems and Digital Services (iJODS)

Veera ALEXANDER - IT Public Engagement Systems, Websites and Enforcement System (iPEWE)

Details on your problem statements and problem formulation process

Problem Statement

How might we help producers (companies) improve the data accuracy for the annual Mandatory Packaging Reporting (MPR) submissions while also enabling NEA officers to efficiently review, validate, and provide clarifications with minimal back-and-forth amendments.

Problem Formulation Process

  1. Understanding Stakeholder Pain Points:

  • Producers face challenges in interpreting MPR data requirements, leading to incomplete or incorrect submissions.

  • NEA officers spend significant time manually reviewing, validating, and requesting amendments, creating inefficiencies.

  1. Defining Key Objectives:

  • For Producers: Ensure clarity in MPR reporting requirements, reducing errors in submissions.

  • For NEA Officers: Automate data validation and anomaly detection to streamline reviews and minimize manual intervention.

  1. Root Cause Analysis:

  • Lack of a structured data validation framework for MPR submissions.

  • Heavy reliance on manual review and clarifications, causing delays.

  • Inconsistent data entries due to varying industry practices and interpretations.

Details on your solution

To enhance the efficiency and accuracy of Mandatory Packaging Reporting (MPR) data validation, we propose an AI-driven approach with two levels of validation:

  1. Automated Data Validation (Level 1):

  • AI-powered validation will check the uploaded Excel data for compliance with predefined formatting rules, mandatory field completion, and the correct selection of dropdown values.

  • This ensures that data submissions adhere to the required structure before further processing, reducing initial errors and minimizing the need for manual corrections.

  1. Predictive Validation Using Machine Learning (Level 2):

  • A Random Forest prediction model will analyze historical data and industry benchmarks to predict the expected weight range submitted by producers.

  • This enables the system to flag anomalies or inconsistencies in reported figures, allowing NEA officers to focus on high-risk submissions that require further review.

  • By leveraging AI-driven insights, the validation process becomes more efficient, reducing the manual effort required for clarifications and amendments.

This two-tiered validation approach will streamline the submission process for producers while significantly improving the accuracy and efficiency of NEA's data review procedures.

Impact and outcomes analysis of your solution

The proposed AI-driven data validation solution can be structured into two key categories: Optimize and Elevate.

Optimize

  1. Enhance Data Accuracy – AI-powered validation ensures data completeness, correctness, and consistency, reducing errors in Mandatory Packaging Reporting (MPR) submissions.

  2. Streamline Submission Processes – Automated checks and predictive analysis simplify data validation, minimizing back-and-forth clarifications with producers.

  3. Increase Operational Efficiency – Reduces manual effort for NEA officers, allowing them to focus on high-value tasks and complex cases.

  4. Improve Decision-Making – Data-driven insights help NEA officers identify anomalies and trends, enabling proactive regulatory actions.

Elevate

  1. Innovate User-Centric Solutions – AI-driven automation enhances the user experience by guiding producers through the submission process with greater clarity.

  2. Enhance Public Trust – Reliable and transparent data validation fosters confidence among stakeholders in the integrity of the reporting process.

  3. Strengthen Data Privacy and Security – AI-enabled validation ensures compliance with data governance standards, reducing risks of misreporting and data breaches.

  4. Foster Cross-Agency Adaptability – The scalable AI framework can be extended to other regulatory reporting systems, promoting interoperability and collaboration across agencies.

Future steps for your project

Next Steps

  • Integrate the AI-driven validation solution into the WRMS system's Mandatory Packaging Reporting (MPR) track and progressively expand its capabilities to other tracks within WRMS.

  • Define a comprehensive product roadmap to facilitate deployment within a centralized system, ensuring seamless service access for various government agencies.

Support Required

  • To scale this initiative into a robust and sustainable product, a well-structured administration module and supporting tools must be developed, ensuring alignment with the GCC 2.0 or GCC+ environment.

  • Securing sponsorship will be crucial to funding the development and implementation of this solution.

This approach will ensure the project's successful integration, scalability, and long-term impact.