Examples of Akai Kaeru at Work in Advancement Analytics
Akai Kaeru’s Explainable AI for Advancement Analytics
Our software can quickly identify the conditions under which features become important and then uncover the causal relations that connect them. First, our pattern mining engine identifies groups of data items with shared characteristics. These patterns are then passed on to our easy-to-use interactive Visual Pattern Explorer where analysts can inspect and act upon them. Use cases in Advancement Analytics include:
Devise Profitable Fund Raising Strategies for a Large Public University
This study uses a dataset we obtained through collaboration with a public university with over 50,000 under-graduate and graduate students and over 24,000 faculty and staff. The dataset has 168 attributes covering demographic and academic information as well as donations for 2,054 donors (1,093 managed and 961 unmanaged). The goal was to identify regions in this feature space that are occupied with similar donors that all respond in a similar way to a given target variable of interest, here the type of donation. All data refer to the year 2018 and earlier.
We used AK Miner to identify groups of donors for which Lifetime Endowments were unusually high or low. These groups were statistically robust and defined by simple criteria (e.g., donation history, demographics, type and origin of degree, etc.). We then switched to AK Visual Pattern Explorer to view and further explore this information, as seen in the figures below.
Further explorations of this dataset using our software reveal many more valuable insights, such as:
Our software makes finding all of these insights as easy as a click of a button. We conducted the entirety of our Advancement Analytics study in a couple of hours. You can read about the details of our study, and how we arrived at these results, in the slides and paper posted here.