We build a cross-sectional factor model for investors’ direct stockholdings, by analogy with standard time-series factor models for stock returns. We estimate the model using data from almost 10 million retail accounts in the Indian stock market. We find that stock characteristics such as firm age and share price have strong investor clienteles associated with them. Similarly, account attributes such as account age, account size, and extreme underdiversification (holding a single stock) are associated with particular characteristic preferences. Coheld stocks tend to have higher return covariance, suggestive of the importance of clientele effects in the stock market.