×
DMA: Data and Marketing Association
Consumer Help

DMA Analytic Challenge

Proving that smart analytics is at the root of profitable data-driven marketing…

The DMA Analytics Community organizes this Analytic Challenge, to engage the best analytic experts from around the globe to solve to a challenging business problem. Data practitioners and academicians go “head-to-head” to build advanced analytic models to find compelling solutions to support a real-world marketing challenge. Each challenge has a Corporate Partner, a Challenge Partner and Challenge Participants.

Thanks to our Challenge Partner
DataLab USA logo

Be A Challenge Partner

Data service members have provided the infrastructure and personnel to run the competition, scrub data sets for the needed fields, anonymize the data if needed, provide secure online platform for participants models and score the models. That partner will award prizes to winners and report on trends during the &THEN conference session and again on a webinar later in the year. The Challenge Partner is showcased in many ways during the process. Find out more about being a Challenge Partner by sending an email.

Find out more about being a Challenge Partner by sending an email to DMACommunities@ana.net.

Be a Corporate Partner

Publishers, direct response retailers, healthcare clinics and nonprofits have been Corporate Partners who provide the business problems, related data sets (to be anonymized) and optionally, awarded prizes for the challenge participants. (Cash prizes are not required and are completely optional). Each Corporate Partner receives the winning model (valued at thousand of dollars) for in market use along with 5 days of support at no charge.

We’re interested in your tough nut problem. Send a brief description of your analysis needs for consideration.

Be a Challenge Participant

For Analysts, Data Scientists, Academicians and other Participants – Once the problem is identified, the challenge participants from around the globe will build advanced analytic models to find compelling solutions to support a real-world marketing challenge. The three top ranking solutions and their companies will be announced at the Analytics Community Breakfast event and have the opportunity to present their analytic approaches during a session at the DMA &THEN Conference at the MGM Grand in Las Vegas, October 7-9, 2018. They will also present at future DMA webinar later in the year.

See Challenge Guidelines

Sign up now. Solutions deadline September 30.

Analysts, Data Scientists, Academicians and other Participants:

Once the problem is identified, the challenge participants with the top-ranking solutions will be announced at the Analytics Community Breakfast event and have the opportunity to present their analytic approaches during a session at the DMA &THEN Conference at the MGM Grand in Las Vegas, October 7-9, 2018. They will also receive a webinar date later in the year for the DMA. See Guidelines below.

Sharing best practices and facilitating the exchange of ideas allows data practitioners to raise their game and increase the value of their work. Here are some past Analytic Challenge winners and some presentations.

See below with whom we’ve partnered in the past. Want to find out more? Contact us at DMACommunities@ana.net.

2018 DMA Analytic Challenge Guidelines

Overview


The DMA Analytics Community organizes this Analytic Challenge, to engage the best analytic experts from around the globe to solve to a challenging business problem. Data practitioners and academicians go “head-to-head” to build advanced analytic models to find compelling solutions to support a real-world marketing challenge. Each challenge has a Corporate Partner, a Challenge Partner and is open to members for participation.

The Objective


This Challenge has two objectives:

  1. As an industry organization, the DMA focuses on educating the analytic community about predictive analysis, modeling, and data manipulation. The Challenge session and webinar are also intended to teach marketing analytic techniques to event attendees.
  2. Recognize companies that achieve superior performance in analytics.


The Challenge


The 2018 DMA Analytic Challenge is to build the most effective model possible for this problem:

Participants will analyze a set of first-party data provided by a direct marketer of consumer products and develop an algorithm that predicts new customers’ six-month “lifetime” value to the marketer.

Starting Friday, September 14th and concluding Monday, September 24th, participants will build a model and score it on a hold-out sample. Each member participant in the Challenge will receive a data set(s) for model building and validation.

  • No other outside data sets can be used.
  • Submissions must be in R or Python.
  • Only one submission per company is permitted.

The winners will be selected using mean squared error (lowest) overall, and the quality and clarity of the presentation of the prediction methodology and model development process. The top three solutions will be featured during a live session at the DMA &THEN annual conference, October 7-9 at the MGM Grand in Las Vegas. The winning algorithm will also be shared with the direct marketing company for in-market use.

Each member participant in the Challenge will receive a data set(s) for model building and validation. No other outside data sets can be used.

Participants will be required to post a scored validation data set to the competition FTP. This will be used to evaluate and identify the top three solutions. Additional details regarding the evaluation criteria will be provided when the modeling data set is released.


Documentation Requirements

  1. Overall PowerPoint presentation (no more than ten pages) outlining:
    • the technical results showing the accuracy and performance of the model against the validation data set via charts and accuracy diagnostics
    • the explanation of model algorithm/equation- what predictor variables it contains and their relative importance to prediction
    • what each variable means/how it was developed, and a non -technical explanation of how the overall model predicts the accuracy of customer lifetime value
  2. Scoring code must be provided when the scored validation file is submitted
  3. Variable creation – variables that were used in the model, need to be traced from input to coefficient / node (if using a tree-based methodology). This includes all recodes, transformations, and summarizations. This information should be presented in a table, with English labels for variables, and equations (if appropriate) for transformations or recodes.


Judging the Results

  1. Evaluation results – cumulative gains tables – will be reviewed by the Challenge Partner and a subset of the DMA Analytics Community Leadership Council
  2. The Judges Panel will identify winning solutions based on criteria that will be specified with the data packet
  3. The Panel will not know which companies have won, but will know which models were the winners
  4. The top 3 Winners will be notified in September


Winners Presentations Requirements

  1. Winners must prepare a 7-8 minute session presentation and must also attend the DMA Analytics Community breakfast, both to be held during DMA’s &THEN Conference, October 7-9, 2018 at the MGM Grand in Las Vegas.
  2. Each participating company agrees to have a company presenter available at &THEN for the Analytic Challenge session, prepared to present. Note that you will need to register as an attendee for the conference.
  3. There will be a check-in for participating companies prior to commencing the session. Any participating company without a presenter will be excluded from the competition at that time.
  4. The participating company will be allowed to use company logos in the presentation. However, the presentation will be converted to a standard DMA PPT template for presentation consistency purposes. Your logo will be included.

Presentation requirements

This presentation must include the following components:
a) The types of exploratory analyses conducted to select variables used in the model
b) The steps taken with the raw data provided to convert into modeling variables
c) Any variable reduction techniques used
d) The steps undertaken in the modeling process
e) How the final model was determined to submit for the competition

The final presentation must be submitted to DMA by Friday, October 1, 2018.

All presentations will be reviewed and edited for content and educational components. As such, you may be contacted to review changes. Refusal to reveal educational content will be grounds for removal from the competition. By agreeing to participate, you are agreeing to fully share the steps and methodologies used in your model.


Additional Requirements

  1. As a DMA Conference session, the DMA retains non-exclusive rights to the material presented during the Analytic Challenge session

Questions? Contact Lisa Merizio Smith at lsmith@ana.net.

Sign up

Past Challenges, Partners & Winners

2016 — Problem: Build the most accurate model possible to predict customer expected value.

View Video

2016 DMA Analytic Challenge Winners AdTheorent and Data Lab

Partner:
Ernst Young Logo

Co-Winners:
DataLab USA logo
ADTHEORENT Logo

Runner up:

2015 — Problem: Build a model that identifies 1X buyers with the greatest likelihood of making a repeat purchase.

View Presentation

Partner:
Epsilon Logo

1st Place:
UCONN Logo

2nd Place:
DataLab USA logo

3rd Place:
MSC, A Valid Company Logo

2013 — Problem: Patient Re‐Activation – Are patients coming back for the same problem? Different problem?

View Presentation

Partners:
Epsilon Logo

Jigyasa Analytics Logo

Primary Partner
Cleveland Clinic Logo

1st Place:
DataLab USA logo

2nd Place:
Fractal Analytics Logo

3rd Place:
PricewaterhouseCoopers Logo

2010 — Problem: Improve marketing to Lapsed donors through better targeting

View Presentation

Partner:

Primary Partner:
Make-A-Wish logo

1st Place:
DataLab USA logo

2nd Place:
Alliance Data Logo

3rd Place:
Rapid Insight Logo

2011 Problem: Predicting open and click through rates for email marketing campaigns

Partner:
Jigyasa Analytics Logo
 
 
 
 
 
 
 
 
Primary Partner:
Hearst Logo

1st Place:
Global Decision Analytics Team Winning DMA Analytic Challenge
Global Decision Analytics Logo

Most Innovative Solution:
Euro RSCG Discovery team winning DMA Analytic Challenge

2007 — Problem: Build the “best” targeting solution

View Presentation

Partner:
CAC Group Logo

1st Place:
DataLab USA logo

2nd Place:
Alliance Data Logo

3rd Place:
Expedia Logo

Not a DMA Member? Learn more about Membership to Participate!
Join DMA Contact Membership

Login To Your Account