Valeria Stourm

Who they are

This page records the public professional record only. Nothing adverse is recorded and no motive is attributed.

Her affiliation and wider career were not verified for this page, so none is asserted here. What can be said is what the paper did. It took a puzzle from retail loyalty data, customers who do not redeem points although redeeming would save them money, and built a model that separates three explanations: the economic value of the points forgone, the effort of redeeming, and the habit of keeping points in a separate mental account from cash.

Key papers

Stourm, V., Bradlow, E. T., & Fader, P. S. (2015), 'Stockpiling Points in Linear Loyalty Programs', Journal of Marketing Research, 52(2), 253-267, doi:10.1509/jmr.12.0354. Read from the abstract and the text.

Her wider publication record was not surveyed for this page.

Key ideas

The paper's main move is to treat stockpiling as something that can be decomposed. Economic incentives push toward redeeming, since points forgone and the time value of money both count against waiting. The cognitive motive is the nonmonetary cost of redeeming. The psychological motive is that points and cash are booked in separate mental accounts and valued differently.

The authors estimated the model on data from an international supercentre chain and forecast redemptions accurately over an eleven-month holdout period. They found that the behaviour was driven mostly by the cognitive and psychological motives, and they used the model to compare three policy changes, of which automatic redemption raised the forecast redemption rate the most.

They are explicit about the limits. The forecasts take purchasing as given, so they cannot capture changes the policies themselves might cause.

The numbers in the paper

The data describe 346 customers who joined an international supercentre chain's linear programme in January 2008. Only 3 per cent of all their purchases involved a redemption, and 60 per cent of customers never redeemed, although redeeming could have cut the basket price by nearly 30 per cent on average. Of the 137 customers who did redeem, 69 redeemed once, 54 two to four times and 14 five times or more.

Redeemers had baskets about 25 per cent larger and visited 141 per cent more often over the 43 months. The paper's descriptive numbers say who redeems, not what redeeming does, and this site does not read them as an effect of redemption.

What the policy tests showed

The model forecast redemption accurately over an 11-month holdout period. Against a baseline forecast of 3.5 per cent, automatic redemption lifted the rate to 21.0 per cent, removing the cap on how much of a basket points could pay for lifted it to 6.6, and the economic policy lifted it to 4.1. The authors also note that the policy raising redemption most is not the one that is cheapest for the firm: in their comparison the economic policy reduced liabilities at the lowest cost per unit while doing least to raise redemptions.

How this site uses her work

The paper is the main evidence in the article on why loyalty points sit unspent. It is used for the size of the puzzle, for the finding that cognitive and psychological motives dominated in that dataset, and for the limit the authors state themselves, that the forecasts hold purchasing fixed.

---