Black Friday deal
Post-COVID California Property Price Trend Prediction
Post-COVID California Property Price Trend Prediction




Digital technology and data-driven decision making have dramatically changed how restaurants stay competitive or to survive. As food delivery and online reservation become more and more popular, restaurants can hardly operate without using digital and data technologies. With this in mind, RMDS Lab is announcing its next data science competition, Developing an Analytics Dashboard to Improve Restaurant Performance.This quarter’s contestants will be challenged with collecting important data sets and then creating an analytics dashboard that will help restaurants to boost their businesses and improve their overall performance. A grant of $1,000 will be awarded to the grand prize winner, and $500 will go to the runner up.

Everyone who registers for the competition will receive FREE admission to IM Data Conference, and contestants who complete and submit their project will receive a FREE, one-month premium membership to GRMDS platform as well as a certificate of completion.


Contestants will be challenged with building up an analytical dashboard with the datasets provided. Contestants are also welcome to research to get more data utilized in the dashboard. Through data research, analysis, feature extraction, and modeling, contestants should reach solid and meaningful conclusions about improving restaurant performance. Based on various studies, our contestants are expected to develop an analytical dashboard to showcase the business insights discovered in a way that is easily understood by restaurant decision-makers and simple for them to implement to stimulate performance improvement.

We have developed a dashboard as an example that our contestants could take advantage of and continue improving on it. Surprise us with your ideas!

Examples of analytical questions for competitors to explore may include:

• What are the factors influencing customer purchase at physical restaurants vs. online (or through 3rd party delivery)?
• What aspects (food, service, price and ambiance) are valued by customers in each food service type?
• What factors contribute to customer reviews and ratings?
What are the site selection parameters, and what will drive the sales forecasting for a new location (in-store and online sales)?
What type of restaurants would customers prefer? (pick-up/delivery, dine-in)
How do restaurants collect data outside the POS?
What is the optimal restaurant tenant mix per retail plaza or food court?
What is the omni-channel strategy for various types of restaurants?
What is the plug & play restaurant technology or technology stack (if any) for independent restaurants vs. multi-unit restaurants?
What is the industry’s best practice for restaurant business analytics?


All perspectives are welcome! Show us your most valuable insights from your innovative data analytics that could benefit the restaurant industry.


RMDS 2021 Competition Timeline
2021 Competition Timeline




The Problem


This data science competition seeks to collect data and then develop an analytical dashboard to improve restaurant performance. Contestants will be provided with the necessary data to begin with.




Dataset Overview


Participants will need to start with the dataset provided below to perform their analysis. This dataset contains the restaurant information in Los Angeles County. This dataset is published solely for the use of competition, please do not use it for other purposes.

There is also a recommended page for contestants to get access to some possible related datasets, ideas and how to get started in creating dashboards. Participants are encouraged to research and to collect more additional data to make their analysis more sensible and innovative.

⚠ You have to sign in to see the recommended page or download the sample dataset. The data would be available for downloading after the competition begins at September 17.


Download Sample Dataset View Recommended Page

The recommended datasets include:

This dataset comprises demographic data like population, age, sex, race and income, published by the US Census Bureau.

Daily cases for LA County by neighborhood. These files come from a continual Times survey of California's 58 county health agencies and three city agencies.

The Consumer Price Index (CPI) for food is a component of the all-items CPI. The CPI measures the average change over time in the prices paid by urban consumers for a representative market basket of consumer goods and services.

It includes multiple tables for different demographic people movements by race and by region.

It includes data of temperature, wind, and others, summarized at daily, month and year level.





RMDS Lab offers our community a variety of educational resources focusing on data science applications and techniques. You may explore the RMDS learning portal containing various data science courses at

Competitors may use the code “COMPETITION2021” to get complimentary access to our online course on Big Data and AI to Improve Competency and Employability.

Below are additional free resources:

If you have any questions regarding access to training materials and want to learn more about RMDS educational resources, you may use the Forum.



Submission Deliverables


  • Technical report in PDF with names of all team members and team name required
  • Datasets used in .zip folder required
  • Readme on how to run your code and requirements.txt on your development environment required (except for high-school students)
  • CSV of results (Optional)
  • A working prototype like map, web page, apps, Tableau, Excel (Required if no codes submitted)

By submitting to the contest, contestants agree to have their submissions made publicly available.





Impact: What useful business insights are acquired from the proposal? How does this submitted model benefit (or cost) businesses, and what actionable steps are recommended to improve their work?​

Methodology Validity: Document the methodology, mathematics, and economic principles behind the proposal and provide the references or reasoning for your approach. How is the prediction generated and how are the factors weighted sensible? Are the assumptions and limitations of the methodology clearly outlined with suggestions to improve the proposal? Are the quantitative steps of data ingestion, feature engineering, model architecture, and performance optimization valid? How robust is your model?

Reproducibility: Does the solution use coding best practices with workflows and documentation to reproduce one’s work? Are the data ingress and egress pipelines reproducible? Is there a clear presentation of data science work in the documentation?

Usability: Is the information presented in a way that is actionable? Would a member of the general public understand the model, what it means, and what actions to take?

Ability to Deploy: Is getting access to the data realistic? How long is the computation time? How well is the scalability of the system to accept new data sources? How often does it need to be maintained? Is it hard to maintain/update? How much manpower, time, resources are needed to be allocated to maintain the functionality?​

Fair and Ethical Use of Data: Does the solution consider biases in data? Is the data from open and trusted sources?

Innovation: Will the idea have a big impact? How innovative is the approach, selection and weighting of various factors, or how information is displayed and communicated?



Judging Committee


speaker 2speaker 3speaker 4 Richard TangCervantes LeeRichard Foxspeaker 4speaker 4





Stage 1:  Registration


Participants will register on GRMDS. We will send out a confirmation email to all participants upon successful registration. Once you form your team, one representative from your team must fill out the Team Registration Form. Please note that this competition is open to all participants globally. For any questions you may ask it on the Forum.


Stage 2:  Team work and submission


Submissions must include all deliverables and are due Sunday, October 10, 11:59 PDT. Please upload all deliverables to the GRMDS. Place the names of all team members and team name on the technical report. Submission by any individual group member will represent the whole team.


Stage 3:  Evaluation and Final Presentation


Our expert committee will evaluate all project deliverables and select the finalist teams at the Awards Ceremony.



  • First Place

    $1,000 + Certificate

    Complimentary six month premium membership at RMDS Lab

  • Second Place

    $500 + Certificate

    Complimentary six month premium membership at RMDS Lab

  • High School Award

    $500 + Certificate

    Complimentary six-month premium membership at RMDS Lab

  • Rising Star Award

    Considerations for internship positions at RMDS Lab + Certificate

    Complimentary six-month premium membership at RMDS Lab

Winners will also be considered for publishing opportunities with our partners.



Winning Strategies in Data Science: An interview with first place winners of the 2021 Developing an Analytics Dashboard to Improve Restaurant Performance competition

Emma Collert is a second-year student in Oklahoma State University’s Masters of Business Analytics and Data Science. Her previous academic experience was focused on market research, with notable work on non-profit consumer behavior research. Now, her passions for research focus on equity in data and in increasing the accessibility of data-led business policy for small businesses.

Jin Kun Chai is a second-year student in Masters of Business Analytics and Data Science and Quantitative Finance. He started with his studies in accounting, finance, and economics before getting into the realm of mathematics and engineering. He is currently an integration analytics assistant who focuses on software development and continues to move forward with his studies in computer science and engineering to enhance and accumulate the knowledge and skills he needs to solve his computational research interests, primarily in the realm of finance.


John Basora is a second-year student in the Masters of Business Analytics and Data Science program at Oklahoma State University. He acquired his undergraduate degree at OSU in Political Science with a minor in History. He is currently a GTA for Dr. Sarathy and is also a GRA working on a research project for Dr. Lawrence. He enjoys research that targets socio political issues and their effects on economics. John is a staunch advocate for data-driven business strategy for small and big businesses alike.


1. What inspired you to take part in this competition?

Our team chose to participate in the RMDS competition for the opportunity to test our skills on real world data.

2. Tell us little about your competition submission. What results did it yield?

Our competition submission centered on creating a dashboard with a focus on actionable data points relevant for a small business that may be just experimenting with how analytics can shape their success. We focused on providing high-quality analytics in a digestible format, with visual tools to assist in quick and easy analysis without context, data points that could be easily transitioned to KPI’s for over time analysis, and a focus on trend identification.

3. What challenges did you have to overcome while completing your submission?

We had two large and recurring challenges while completing our submission. The first was how to create an actionable dashboard without data over time connected to the restaurants we were presented with. We wanted to retain the initial dashboards, as the information included was outside of the scope for what we could obtain in the given time – but connecting that information to external datasets was difficult, and in some instances impossible. In addition to this difficulty, we also had to evaluate the datasets presented for bias. As we had minimal background on some data pulls; there were several metrics we dismissed out of concern that the data may be misleading due to sampling concerns.

4. What did you learn about data science by taking part in this competition?

This competition provided the opportunity to develop our skills in accommodating requests of future customers or employers, in which an outline for the request may be provided but details are not. We were also able to practice working within an unfamiliar dataset with limited context – a consistent difficulty amongst data scientists.

5. How do you stay motivated?

Our team thrives by surrounding ourselves with positive, innovative, and compassionate people. Whether that is our peers within the program, our mentors, or each other, we stay motivated through the passion for analytics we see in the people around us.

6. What advice do you have for people who aspire to win data science contests?

A refined but high-quality product will always perform better than an expansive, but low-quality product. There are many things we wanted to do – but ended up out of scope for this project due to time limitations or monetary concerns. Ultimately, in work and in contests, you need to find a way to perform well within the confines of the task in front of you. In our case, that meant focusing on a polished and well performing dashboard that met our primary goals – a dashboard that could interface well with those new to analytics, and whose communicated information we could confidently stand behind.

7. What are you working on now?

Emma Collert is currently working on research into the ethical sourcing of data and how the impacts of biased sampling create pervasive and divisive consequences.


Jin Kun Chai is currently working on front-end development focusing on providing the tools and program to enable data being read from external sources securely and visualize onto an open-source dashboard. Other pending tasks are assembler and system development.



John Basora is currently working on a research project involving the effects of policy on service-related industries in the US. This will involve the use of neuro linguistic programming and text analytics.


8. Is there anything you would like to discuss that was not mentioned above?

We would like to thank RMDS for the opportunity to participate and hone our skills within this competition. We are delighted with the results and are thankful that the hard work and considerations invested into this project resulted in this success.



Code of Conduct

The use of data will adhere to ethical use and protection of individual data privacy. Find the Code of Conduct here.



Frequently Asked Questions

How do I register?

We offer two options for registration based on age. For high school students, CLICK HERE. All other contestants can CLICK HERE. You must be signed in to view the form.

How do I form a team?

Participants are welcomed either as individuals or as teams. In the case of teams, one person must be designated as the team leader and will be solely responsible for communications with the organizers. If you are looking for teammates, advertise your interest on our Forum

How do I make submissions and what are the deliverables?

Submissions can be made here. See above section “Submission Deliverables” to see what must be included in your submission.

What is the deadline to register?

There is no deadline for our registration. But we strongly recommend that your registration is no later than August 27, since you need time to prepare your work.

How does the number of team members impact potential cash prize offerings?

The number of team members will not impact potential prize offerings. The prize offerings will remain the same.

Can teams comprise members from different cities/countries?

Yes. We welcome people from different cities or countries to join our competition. This competition is open to the global community.

How do I get in contact with the organizers?

If you have any questions, you may ask in the Forum. We’ll get back to you as soon as we can.

I already registered my team but need to update my team info. What should I do?

If you need to update your team roaster, please submit the registration form again with all the team members information.

What training material do you have to help my team get started?

Please see resources listed on this page, including recordings of competition training sessions. There is also a dataset sample, data dictionary and further reading material.