An ablation study tests the effect of removing or varying selected inputs, features, or components while holding other conditions constant. This helps isolate which change may be responsible for a difference in outcomes. section 3.1.1
Testing age effects in movie recommendations
Give synthetic users identical viewing behavior, vary only their age, and compare the genre distributions of their recommendations. In one diagnostic, Indie recommendations rose from 8.81% for ages 18–24 to 14.30% for ages 55+. Because preferences were held constant, the difference warrants investigation of how age affects exposure; it does not by itself establish bias among real users. section 3.1.1
Listing 3.1 Analyzing Distribution of Genres by Age Group Cohorts
# Calculate the distribution of genres within each age group's recommendations genre_diversity = analysis_df.groupby(['age_group', 'genre']).size().reset_index(name='count') genre_pivot = genre_diversity.pivot(index='age_group', columns='genre', values='count').fillna(0) genre_pivot = genre_pivot.div(genre_pivot.sum(axis=1), axis=0) # Normalize by row to get proportions genre_pivot
The listing groups recommendations by age and genre, then normalizes each age group's counts into proportions for comparison. section 3.1.1




