OpT Health AI is a very cool concept... nice job, Techno4! ... View more

Very important issue, with some good data sources and a very thorough analysis.  Well done, Team! ... View more

Very impressive collaboration and great analysis.  And I really liked the interactive dashboard.  Well done, Team! ... View more

Again, love the way you all are ideating here, @KaranShrestha!  Thank you for the additional detail... I like where you are going here.  Moreover, I completely agree with this statement: In the end, we’re aiming for a process that values diverse strengths and makes admissions more equitable for everyone.  Indeed!   Great work! ... View more

Growth Trajectory Score?  Love the concept!  I'm not familiar with that approach, but do agree that it would worth exploring.  Moreover, some bonus points for engagement is also a nice concept, to better isolate those applicants truly enthusiastic about the program.   Well done @SushantMagar123 - I love how you're thinking through admissions at my fictious university! ... View more

Awww - very nice note, @ryanx0129.  And, again, excellent work! ... View more

Great response, @andrea & Pasqual!  Recapping a months worth of work in 10 minutes is never easy... and I appreciate the added detail provided above.  Moreover, I appreciate how critically both of you have thought about the challenges at hand.   Again, great work! ... View more

Whoa.  Just a fantastic idea with meaningful research and great execution.  Well done, @NEAR Exergame!!! ... View more

Excellent work, @DataNinjas!  I loved the framing you used to highlight the challenges in using historical data to predict the incoming class.  Moreover, your interactive data analysis/exploratory data analysis did a great job of level setting before hopping right into the modeling.  With the modeling, I really like how you broke bias into performance bias and prediction bias... nice work!  Finally, nice work in diving into the tradeoffs between model performance and fairness in outcomes... One question: if you could wave a magic wand, which new variables would you want to collect in the admissions process to make the admissions process more equitable? Great work! ... View more

Love this: "model accuracy is not the only consideration factor for us"! Yes!   Great analysis, @HotSirapBandung!  I love the analytics lifecycle approach utilized in your analysis, which took us from SAS Studio to SAS VA to SAS Model Studio.  The real time modeling also showed how proficient you are with the software, which is - put simply - impressive.  Moreover, I love that you uncovered that Legacy Admission was one of the most problematic variables in the analysis... So, summing up in two words: GREAT JOB! ... View more

Wonderful job @TheItalianJob!!!  You did an excellent job of creating an easy-to-follow analysis using both SAS Visual Analytics and SAS Model Studio.  In particular, I like how you carefully walked through the descriptive statistics - complete with maps - in SAS Visual Analytics.  You then used the Fairness + Bias Assessment tools in SAS Model Studio to refine your models to make the offers of admissions more equitable.  Finally - I love the recommendations for improving data collection at iLink University in the future... Yay! One question: did you notice any issues with the Legacy Admissions variable?  I purposely made it biased, and highly predictive, and was wondering what you saw in your model.  Regardless, great work! ... View more

What a Pitch Video... that was great!!!  Way to bring my fake university to life!   And, overall, great job with your analysis.  I liked how you explained the models under consideration and examined the strength of the predictors across a range of model specifications.  Moreover, I liked the Cluster Analysis flow as a way to make the descriptive statistics a bit more accessible. A couple of follow-up questions: did you use any of the Fairness + Bias Assessment tools in SAS Model Studio?  And how did you weigh the tradeoff between select variables (i.e., gender/legacy admissions/cultural identity) and overall model fit? Again, nice work!   ... View more

Wonderful framing and video, @LosTonotos!  I loved how you made your analysis accessible, while incorporating more advanced analytical tools like principal components analysis and k-means clustering.  Additionally, I liked how you incorporated the latest storm videos, to remind people that the impacts from climate change are a very real - and present - danger.   My only suggestion is to include a bit more GeoMapping in your analysis.  GeoMaps are a great way to distill a LOT of information... and share that quickly with your reader.  Otherwise, great work! ... View more

Very nice work, @TGTBT!  I love how critically you thought about the data and how you pulled everything together in your presentation.  Moreover, it's great to see that you create a new index - the Worrisome Score - as a way to combine several measures into a single metric.   I noted that Wake County was number 50 on the list.  Whoa.  I live in Wake County... and it's also the location of SAS HQ.  So, I was a bit surprised to see us on the list... given that we're not near the coast in a traditional "hotspot" for weather events.  In investigating your Worrisome Score a bit more, I'm wondering if the population measure isn't driving things a bit too much.  In fact, the top 50 counties are all large - and I didn't see any traditional rural/isolated counties in the list.  So, for robustness, I'd love to see your results if you (1) normalized all the subcomponents to range between 0 and 1 (you can do that with a standardized Z-Score) and then (2) aggregate the variables, as specified in your current approach. Wake County concerns aside, great job!!! ... View more

Wow - great job, @ORSOL!  I love the way you followed the data analytics lifecycle in your jury video.  Moreover, I was impressed with your Credit Risk Factor Scoring System, as a way to create meaningful insights from A LOT of data.  Finally, I see that you were able to create a map with all the counties in the U.S., which tells me that you spent significant time cleaning the underlying data and were successful... And last but not least - great dashboard... and way to end with ways to improve! Excellent work! ... View more