Quality Control and Reliability Engineering (QCRE) Division Data Challenge Competition

Eligibility

Individuals or teams of a maximum of four members.
At least one of the team members must be an active member of the Institute of Industrial & Systems Engineers (IISE) and Quality Control & Reliability Engineering (QCRE) division.
Each team can only participate once. Each member can only be involved in one team. Each team should submit a Notice of Intent Form to enter the competition (check details in the Notice of Intent section).
Completing Steps 1-2 in the Submission section is required for any team to be eligible as a finalist.
Trained model weights must be submitted to the Competition Steering Committee for verification, but must not be publicly released or redistributed without prior written approval from the data provider (Five Star Management Group).
Participants are strictly prohibited from sharing the challenge dataset publicly. Any team intending to publish work that utilizes the dataset must obtain prior approval from the data provider (Five Star Management Group).

Notice of Intent (NOI)

Each team must submit a Notice of Intent Form through https://forms.office.com/r/Dd7UsUAV3C to express their interest in entering the competition. We accept NOI until March 10, 2026, but encourage each team to submit the NOI as early as possible.

The data will be released to the team's point of contact. The NOI form requires the following information: Team point of contact (name and email address), Team members (Name, Degree, Institution, and Email), and Copyright release agreement.

Submission Guidlelines

Step 1: File Submission

Participating teams or individuals must submit the following files to iiseqcredcc@gmail.com and copy all the Chairs of the Competition Steering Committee no later than March 27th, 2026, 11:59 PM CT.

File 1: The source code for model development and training.
File 2: The detection code for the test data (“detection.py”).
File 3: The trained model weights.
File 4: The detection results for test data (“test_detection.csv”).
File 5: Report

Files 1-3 Structure

The submitted files should follow the structure below:

|- DataFile

|- train_data (empty)
|- test_data (empty)

|- trained_weights
|- train.py
|- detection.py
|- ReadMe.md

The primary script for generating detections must be named “detection.py”. This script should be capable of directly loading the trained model weights, reading image files from the test_data folder or any other designated held-out test dataset, and producing the corresponding detections. It is imperative that the detection script “detection.py” runs without requiring any modifications. Any necessary software dependencies should be explicitly stated in the submission. Additionally, a ReadMe file must be included, providing clear instructions on how to execute the code.

Trained model weights will be used only for submission verification and judging and will not be shared outside the Competition Steering Committee and designated evaluators.

File 4 Detection Results ("test_detection.csv)

The test dataset will be released to each team (shared directly with each team’s designated point of contact) two days before the submission deadline on March 25, 2026, 5 PM CT. The detection results (“test_detection.csv”) should include each image_id in the test dataset, defect result, and defect type (DT) (if it is a defect). The table below is the expected “test_detection.csv” columns, with 1 meaning Yes, and 0 meaning No. The meaning of DT1-3 is provided in the problem description.

image_id	defect	DT1	DT2	DT3
xx1.png	1	0	1	0
xx2png	0	0	0	0
xx3png	1	1	0	1

File 5 technical Report Submission

Each team will be required to submit a technical report (format with 1-inch margins, single column, single-spaced, 12-point font, in Times New Roman, not exceeding six pages, excluding references). The report should include the following sections:

Team Members: Name, full affiliations, contact information (email), and roles. Identification of one team member as the primary contact for the team.
Introduction: Overview of the problem and motivation.
Methodology: Description of the approach, models, and techniques used.
Data Analysis/Result Discussion: Insights derived from the data and model performance.
Conclusions:Summary of findings and implications.

Finalist Presentation at the IISE Annual Meeting

Finalist teams must present their work at the 2026 IISE Annual Conference & Expo. At least one team member from each finalist team is required to register for the conference and present their technical details during the QCRE Data Challenge Competition session. Each presentation will be evaluated by invited judges to compete for the final rank.

For any further inquiries, please contact the Chair of the Competition Steering Committee.

Evaluation

Selection of Finalist

The Competition Steering Committee will assess submissions based on the files specified in Step 1 of the Submission section. Only teams that have submitted all the required files in Step 1 will be considered for evaluation. The evaluation committee will include at least one representative from the data sponsor partner with domain expertise.

The model performance will be measured based on

Score = 0.6*PoB+0.4*PoM
Performance of Binary (PoB) =Accuracy + F1Score (micro)
Performance of Multiclass (PoM) =Accuracy + F1Score (micro)

The Score value will be used to rank each team (RScore). A maximum of four teams (RScore 1 to 4) with the highest Score will be selected as candidate finalists. Finalists will be invited to proceed with Step 2 outlined in the Submission section.

Selection of Winner

The eligible finalist teams will present their results at the 2026 IISE Annual Conference. Each presentation will be evaluated by invited judges based on the following criteria: 1) Data Understanding & Preparation; 2) Methodology & Technical Soundness; 3) Results & Evaluation (please report the average inference time (second) per image in the test data and hardware setting); 4) Insights & Interpretation; 5) Presentation Quality & Communication; 6) Practical Deployment Considerations. The evaluation results will be used to determine the rank RPresent value. The final rank of each team will be based on this formula.

Final Rank = 0.6*RScore+0.4*RPresent

For any further questions, participants may reach out to the Competition Steering Committee.

Important Dates (Deadlines)

Notice of Intent (NOI): March 10, 2026, 11:59 PM CT
Training Data Release (first-come, first-served): February 20 – March 10, 2026
Test Data Release: March 25, 2026, 5:00 PM CT.
Submission Deadline: March 27, 2026, 11:59 PM CT
Finalist Notification: April 6, 2026
IISE Annual Conference & Expo: May 16–19, 2026

Recognition

A maximum of the top four teams will be selected as finalists and will receive both a certificate and a monetary award based on their ranking. All the eligible finalists will also be recognized in the QCRE town hall meeting. If a team is unable to meet any item in the Eligibility section, the team may be excluded from the finalist selection. In this case, fewer than four teams may be awarded.

The 1st prize comprises a certificate and a cash prize of $1,400.
The 2nd prize comprises a certificate and a cash prize of $700.
The 3rd prize comprises a certificate and a cash prize of $300.
The 4th prize comprises a certificate and a cash prize of $100.

Committee Chairs

Chao Wang
The University of Iowa

Haifeng Wang
Mississippi State University

Conflict of Interest Policy

Societies and divisions must follow standard conflict of interest guidelines. Those guidelines include, but are not limited to:

Officers and Board members of the Division should be ineligible for awards during the period of their service, without approval by the Senior VP for Technical Operations (SVP). Exceptions may only be made by the SVP when awards are time sensitive, and the impacted board member(s) or officer(s) must recuse themselves from the award process. For awards that are not time-sensitive, the nominee should wait until their Officer or Board service is complete to be nominated.
The awards committee (or judging committee) should not include members who have either a personal or professional relationship with the nominees. For example, a faculty member should not be judging a paper competition where a participant from the same university is a nominee for best paper award.
The awards committee (or judging committee) should actively change its membership on a rotating basis from year to year to ensure fairness, equity, and diversity. That is, some members of the judging committee should roll off the committee and new members should roll on.

2025 Winners

1st Place

Chand Sahil Mansuri, Shriya Madhwani, and Emad Abed
Binghamton University

2nd Place

Shashank Galla, Haopeng Tian, Abhishek Hanchate, and Yuhao Zhong
Texas A&M Univeristy

3rd Place

MD Shafikul Islam, Azmine Toushik Wasi, Mahfuz Ahmed Anik, and Wahid Dhrubo
Louisiana State University (USA) and Shahjalal University of Science & Technology (Bangladesh)

QCRE Division Webpage