Week 5: Starting testing

Good morning blog followers. I apologize for not writing this last night per usual. I was at Grace Hopper this past week and did not have much time to work on the project. Next week I will be off for a week as my term will be coming to an end. I plan to continue working on the project, but I may not post next Monday and instead will write a long report the following week. Briefly, here's what I discussed this week with the graduate student in charge of the project.

Task

The goal this week is to start developing and testing one of the tools. Between the build-a-rank tool and the explain-a-rank tool, the explain tool makes more sense to me to start with. My plan is to learn about a regression version of the random forest classifier (I think it's called random regression?) and modify it to fit our needs. Here is my strategy for developing the tool.

Dummy Test Cases

One will be really simple, like with only one attribute. For example, the set Fruit, A1: apple, 2; banana, 4; pear, 5. If I gave the tool the ranking "apple, banana, pear", it should return "A1, ascending" as the attribute that explains the rank.

Another will be a bit more complicated by having a few attributes (e.g. Fruit, A1, A2: apple, 2, 10; banana, 4, 9; pear, 5, 2). If I gave the tool the ranking "pear, banana, apple", it should return "A2, descending".

Assumptions

For now, I will assume all attributes (except the prediction one) are continuous. I will also assume all the rankings are of equal distance (2 - 1 == 3 - 2 == 4 - 3).

Goal

Using one year's worth of college facts from CollegeScorecard, I'll create a couple different rankings by artificially weighting attributes. I should be able to learn those weights and the attributes to which they are applied by using my algorithm.

 See you in two weeks, hopefully with some solid results!

Comments

Post a Comment

Popular posts from this blog

Week 31: Datasets for fairness

This week, Diana and I looked for some datasets on which to evaluate our fairness criteria. This is no simple task. For one, the datasets need to be large enough to be split into training, calibration, and testing sets. Second, there needs to be some protected group attribute like sex, race, or age. Third, there needs to be some outcome ranking as well as some truth value. The truth is often the hardest attribute to find. In this post, I introduce some of the datsets we decided to use. I try to identify each of the necessary features that we need to properly test our fairness criteria. COMPAS The COMPAS dataset is an obvious choice because it is well ingrained in the literature about fairness. It has 18,000 observations (n=18000) and 1000 attributes (k=1000). Protected groups can be sex (81/19) or race (51/49). The outcome attribute can be the recidivism score, the score used in court that represents the risk that the accused will commit another crime. The truth attribute is a li...
Read more

Week 32-33: Wrapping up

Hi all. This is my last blog post for this project. The last few weeks, we spent little time working on the project and instead focused on finishing up our classes. To be honest, we lost some motivation after finishing the paper, and we've been reluctant to start up new tasks so close to the end of the year. In this post, I'd like to talk about some of the things I've learned in this project other than what we found in our research. This post is really more a service to myself; to help me reflect on this past year and what I've learned. When I started this project, I didn't understand how research in computing worked. My exposure to research had been more biology/clinical, in which research involved setting a hypothesis about some protein, designing an experiment with positive and negative controls, and then running the experiment repeatedly until confident in the results. In computing research, my experience has been of two varieties: reading papers and proce...
Read more

Week 30: Returning to Fairness

With the LineUp paper submitted, it's now time to return to the fairness problem we were working on before. As a bit of a refresher for you and for me, I'll review what we've done with fairness so far and what remains to be done. Fairness in Ranking Up until now, the literature regarding fairness has focused on fairness in classification. As an illustrative example, consider fairness in hiring practices with repect to applicant sex. A job opening might receive 100 applicants evenly split into 50 males and 50 females. If males and females are equally capable of doing the job, then you might be concerned to see the hiring company mostly interviewing male applicants. To evaluate fairness, you would compare each applicant's capability (capable of performing duties, not capable) to their outcome (interviewed, not interviewed). In a completely fair scenario, the same proportion of capable applicants from each sex group would receive an interview. Small deviances from this...
Read more