# Hershey deploys AI shelf-planning to cluster s'mores ingredients, drives seasonal lift

*AI tool optimizes placement of chocolate, marshmallows, and graham crackers during peak camping season.*

By **Jenny Huang Goodman MPA MSc MHSA, Principal** — The Stash Edge, Hako Shikin LLC.
Published 2026-08-24.

Canonical: https://www.pops4.com/stash/articles/hershey-2026-08-24t18-4
Subject: Hershey
Tags: ai, shelf strategy, seasonal merchandising, retail clustering, occasion marketing, hershey

---

According to Modern Retail, The Hershey Company has begun using AI tools to maximize sales performance of s'mores ingredients in stores during the season. The move targets not just its own chocolate bars but the entire consumption cluster: marshmallows and graham crackers positioned together on shelves when camping season opens.

The mechanism is straightforward. Hershey's AI analyzes historical sales data, regional weather patterns, and seasonal behavior to identify optimal timing and placement for s'mores ingredient displays. The tool recommends which stores should receive expanded allocations, when to shift shelf space from everyday chocolate to seasonal clustering, and how to position complementary products from other brands. The result is higher basket sizes when consumers see the full recipe assembled in one place, rather than hunting across aisles.

This works because s'mores are an occasion purchase, not an ingredient purchase. A shopper buying chocolate bars for general snacking rarely buys marshmallows. But a shopper primed by Memorial Day weekend or a camping trip who sees all three items grouped together converts at a higher rate. The AI identifies the narrow windows when this clustering pays off and the geographic markets where it matters most. A store in Colorado gets a different s'mores plan than a store in Florida.

The broader principle is multi-product occasion mapping. Hershey does not control the marshmallow or graham cracker shelf, but it can use data to show retailers that clustering drives category lift. The AI provides the retailer-facing argument: here is the revenue gain from co-locating these SKUs for these four weeks. Retailers respond to margin math, and the AI generates that math at store level.

For a small physical-product brand, the steal is simpler than it sounds. Identify the occasion where your product is one ingredient in a larger ritual. Map the other products in that ritual, even if you do not make them. Build a one-page retail proposal showing historical sales lift when those products sit together. Use free tools like Google Trends to show seasonality by region. Approach the buyer with a plan: your product plus three complementary SKUs, four-week end-cap test, split by control stores. Offer to supply shelf talkers or recipe cards that name all the ingredients. The cost is design time and print, not media spend. The argument is margin accretion, not brand awareness.

If you have budget, layer in a simple predictive model using your own sell-through data. Export your sales by week and region for the past two years. Run a basic regression against local weather, holidays, and school calendars. Identify your top three conversion windows. Walk into the buyer meeting with a chart showing when your category spikes and a merchandising plan timed to those weeks. You do not need Hershey's AI. You need their logic: sell the occasion, not the SKU.

The next play is cross-category data partnerships. Hershey likely shares anonymized point-of-sale data with marshmallow and cracker brands to build the clustering case together. A small brand can do this informally: reach out to a complementary product maker in your channel, share sales curves, and co-author a retailer pitch. Two brands with aligned seasonal peaks and a joint margin story get shelf space that one brand asking alone does not.

## The takeaway

Map the full occasion ritual around your product, then sell retailers on clustering the ingredients during narrow seasonal windows.

---

## Publisher

**Hako Shikin LLC** — Virginia Beach, Virginia. Founded 1997. ASI 217876 · DUNS 18-204-6339.
Principal and author: **Jenny Huang Goodman MPA MSc MHSA**.

- Author: https://www.huanggoodman.com/about
- LLM context: https://www.pops4.com/stash/llms.txt
- MCP endpoint, for AI agents: https://mcp.pops4.com/mcp
- Client dashboard: https://dashboard.pops4.com/
- Catalogue: 70,000+ products, 200+ brands