15.570  Digital Marketing & Social Media Analytics

Marketing Innovation at PayPal using Data Science

Hi all -

The data analytics club is organizing a talk tomorrow on Marketing Innovation at PayPal, which we think you might find interesting. Details below:

Tuesday, 9 Dec 2014
Marketing innovation at PayPal: understanding customers through data science
11:45am-12:45pm E62-250

Farah Hussain and Lei Ding will introduce one of the most recent "big data"-driven marketing innovations at PayPal, where marketers and data scientists work together to uncover unique opportunities to generate business results. Through creating and operationalizing predictive models, marketers have been able to reach large audiences with content tailored to consumers' interests. In addition, we will show through examples what we believe is the best way for cross-functional teams to collaborate and enable innovation in a large enterprise.

Speakers
Farah Hussain, Senior Marketing Manager, PayPal Media Network
Farah Hussain leads the marketing team at PayPal Media Network based in Boston. Her past marketing experience includes roles at Intuit Inc., Ocean Spray Cranberries, and Racepoint Global. In 2011, she was the winner of the Nan Langowitz Women Who Make a Difference Award for her entrepreneurial contributions to MBA student career development at Babson College. Farah is currently the Boston site leader for eBay Women in Technology, and a mentor with the PayPal Start Tank, an incubator designed to accelerate the growth of the Boston start-up ecosystem. Farah has an MBA from Babson College and BA from Wellesley College.

Lei Ding, Data Science Manager, PayPal
Dr. Lei Ding leads the Data Science team for Marketing and Demand Generation at PayPal. In this role, he is responsible for the design, architecture, development, and quality of systems that operationalize data science at scale. Before, he led Data Science at Intent Media, a advertising startup headquartered in New York. He contributed significantly to online predictive systems that served millions of visitors each day on a number of premium e-commerce websites. Earlier in his career, he conducted applied R&D at several leading research labs including IBM Watson Lab. He received a PhD degree from Ohio State, and studied management at Stanford.

Best,
Parul

Announced on 08 December 2014  7:00  p.m. by Parul Batra

Bring your laptop to class tomorrow

Hi all,

We are setting aside a portion of the class to complete online course evaluations; please bring your laptop to class.

See you tomorrow!

Best,
Sinan, Noel, Parul

Announced on 08 December 2014  6:56  p.m. by Parul Batra

Recitation Material and other helpful resources for the final project

Hi all -

We hope the recitation today was helpful to those of you who attended. All of you can watch the video from the recitation at the link I just sent out in my earlier email.

A few announcements:
1. We have uploaded both R and Stata sample code from the recitation on Stellar under the "Group Project Materials" section. We have written extensive comments in the code, so you can understand each statement. We have only been able to demonstrate the most useful functions in the sample code. However, there are a ton of free online resources available on the web for both R and Sata, in case you want to explore additional functionalities.

2. For those of you analyzing the data in excel, you can use the "StatPlus" add-in with excel on both PC and Mac. The 'StatPlus' add-in allows you to easily create visualizations, and run linear and logistic regression in excel. You can download the software and use it for free for the first 30 days at this link:http://www.analystsoft.com/en/products/statplus/

3. While running regressions, if you need help in interpreting the outputs of the regression models, there are a number of online resources which will be helpful. We dug around and found some resources which do a great job of explaining how you can interpret the coefficients and other statistics (p value, odds ratio) in the output of linear and logistic regression.
Linear regression:
a. http://blog.minitab.com/blog/adventures-in-statistics/how-to-interpret-regression-analysis-results-p-values-and-coefficients
b. http://www.ats.ucla.edu/stat/sas/faq/sas_interpret_log.htm

Logistic Regression:
a. http://www.ats.ucla.edu/Stat/stata/library/sg124.pdf
b. http://www.ats.ucla.edu/stat/mult_pkg/faq/general/odds_ratio.htm

4. We know that many of you were confused about the time periods in the dataset (current, past, post, delta1, delta2). We hope that our email describing delta1 and delta2 was helpful in making things somewhat clear. We have created a visual graphic that may further help you understand the different time periods, and the definitions of delta1 and delta2 variables. The graphic titled 'timeline' is uploaded on Stellar under the "Group Project Materials" section.

Sorry for the long email, but hopefully this material will be helpful to you in the last stretch before the final deliverable. We know you have all been working hard! Good luck with this final stretch!

Best,
Parul and Noel

Announced on 05 December 2014  8:37  p.m. by Parul Batra

Video recordings of all lectures and today's recitation

Hi all -

We have recorded all the lectures in 15.570, as well as today's recitation on video. You can watch the video from any of the lectures or today's recitation at the following link:
http://mitsloan.mediasite.com/mediasite/Catalog/catalogs/15570-digital-marketing-social-media-analytics-2014fa

The videos should be available till end of December.

Best,
Parul

Announced on 05 December 2014  8:12  p.m. by Parul Batra

Room for Tomorrow's Recitation (12/5)

Recitation will be held in E62-262 (our regular classroom) between 4-5 pm tomorrow 12/5. Please make sure you have the necessary software package (R or Stata or Excel) installed on your laptop before 4 pm tomorrow, so we can jump into technical exploration of the software at 4.

See many of you tomorrow!

Best,
Parul

Announced on 04 December 2014  1:43  p.m. by Parul Batra