What We — Leave Behind

If your project is a on human legacy, deep features can quantify abstract concepts:

To build a deep feature using a tool like Featuretools, follow this workflow: What We Leave Behind

: A deep feature could aggregate the frequency and variety of digital interactions over time to measure the "weight" of a person's digital remains. If your project is a on human legacy,

: Specify the max_depth . A depth of 1 might calculate "average session time," while a depth of 2 could calculate the "average of the maximum session times across all devices". : Run the DFS algorithm to output a

: Run the DFS algorithm to output a new "feature matrix" containing these high-level, multi-layered insights. Applications for "What We Leave Behind"

: Identify your "base" table (e.g., Users ) and related tables (e.g., Digital Footprint , Physical Artifacts ).

: By applying mathematical functions to time-series data, you can create features that predict how quickly certain "left behind" artifacts lose relevance or visibility.