Data 607 - Assignment 11

John Kellogg

2019-11-10

LinkedIn Recommendation Systems - focused on finding “like” people

Assignment ask

Your task is to analyze an existing recommender system that you find interesting. You should:

  1. Perform a Scenario Design analysis as described below. Consider whether it makes sense for your selected recommender system to perform scenario design twice, once for the organization (e.g. Amazon.com) and once for the organization’s customers.

  2. Attempt to reverse engineer what you can about the site, from the site interface and any available information that you can find on the Internet or elsewhere.

  3. Include specific recommendations about how to improve the site’s recommendation capabilities going forward.

  4. Create your report using an R Markdown file, and create a discussion thread with a link to the Git Hub repo where your Markdown file notebook resides. You are not expected to need to write code for this discussion assignment.

Scenario Design model

Scenario Design model

Task 1

  • Perform a Scenario Design analysis as described below. Consider whether it makes sense for your selected recommender system to perform scenario design twice, once for the organization (e.g. Amazon.com) and once for the organization’s customers.

Scenario Design for the organization

1. Who are your Target users?

As a company, LinkedIn’s target users are professionals of any job function or industry.

2. What are their Key Goals?

The professionals are looking to ‘link up’ with other professionals and be introduced to new professionals of similar mindsets in a professional manner.

3. How can we help them accomplish those goals?

Offer a business focused social platform which allows our users to keep up and interact with the people they know AND introduce themselves to others they would have never met otherwise.

Scenario Design for the customers

1. Who are your Target users?

As a user, my target users are professionals which share some aspect of my job function or preferred knowledge set.

2. What are their Key Goals?

As a user, my target users are professionals of whom I have some prior interaction with which will lead to “linking up” with the people they know. As a secondary goal, LinkedIn puts me in ‘personal’ reach Recruiters I would have never met and are looking for someone like me.

3. How can we help them accomplish those goals?

This goal does not change, the site offers a business focused social platform which allows our users to keep up and interact with the people they know AND introduce themselves to others they would have never met otherwise.

LinkedIn’s strength in finding people

LinkedIn’s strength in finding people

Task 2

  • Attempt to reverse engineer what you can about the site, from the site interface and any available information that you can find on the Internet or elsewhere.

The AI Behind LinkedIn Recruiter Search and Recommendation systems (Qi Guo, et al. 4/22/2019)

Linkedin engineering wrote an article which covers part of their Recommender engine. They utilize a “talent search domain” system They state, “Unlike traditional search and recommendation systems, which solely focus on estimating how relevant an item is for a given query, the talent search domain requires mutual interest between the recruiter and the candidate in the context of the job opportunity.” Unlike other discussed recommender systems, both the interested party and the interested recruiter has to demonstrate interest in the opportunity or job. They also use this same model for creating a connection between individuals unless you expressly state it both parties have to accept the request even if generated in the potential connections section.

As to the interface of the site, it has a very familiar look and function. It comes as no surprise the home page, messaging system, and notifications system mirrors that of Facebook. LinkedIn wants to be the business professional “Facebook”. The posts on the main page are work anniversaries and promotions; the articles are focused on your experiences (they have your resume after all).

Task 3

  • Include specific recommendations about how to improve the site’s recommendation capabilities going forward.

Improvement here is challenging without expanding the scope. They are not so e-commerce driven as the other social media platforms; they do have advertisements in the post stream. There is a “news” function in an attempt for the user to stay up to date while not leaving the site.

I would start the investigation into the mobile App side driving better recommendations. If the user allows, GPS coordinates to be fed to the app, then the recommender could easily track not only other professionals around them in large numbers (conventions) but other like minded people in area of most frequency (the coffee shop you stop at every day).

Task 4

  • Create your report using an R Markdown file, and create a discussion thread with a link to the Git Hub repo where your Markdown file notebook resides. You are not expected to need to write code for this discussion assignment.

File will be place in RPubs. Link to pub file will be linked to the discussion board.