Background image: Merchandise Planning Banner 2

Merchandise Planning: A Mix of Art and Science 

Transforming Retail: The Intersection of AI, ML and Data Management in Merchandise Planning

In today's dynamic retail sphere, merchandise planning is undergoing a profound transformation. Traditionally, future decisions were based on past assortment performance, enabling informed predictions rooted in familiar patterns and trends.

However, advancements in technology are shifting the tides. The significance of last year’s sales data alone has diminished in the face of a complex retail landscape. Changes in consumer behavior, supply chain disruptions, and short-term projections have complicated decision-making.

Merchandise planning is increasingly becoming a layered mix of art and science; artificial intelligence (AI) tools and visual complements are elevating the art of leveraging novel insights that can be derived from the science of data collection.

The Science: AI, Machine Learning & the New Data Ecosystem

The rapid evolution of AI and machine learning (ML) is a key pillar of this paradigm shift. AI and ML can both analyze massive amounts of internal and external data to help drive strategic decision-making at a faster pace.

The retail industry is witnessing a surge in data availability from diverse sources – market research, competitor insights, product lifecycle management (PLM) systems, and digital product development. A crucial advancement lies in dissecting data from these sources with novel precision. Merchandise planners can now decipher granular trends, identifying specific shades or size-fit dynamics that resonate with varying consumer preferences.

Insights into sellouts, pricing, customer sentiment, and promotions offer untapped value through AI’s ability to gather data available on websites. ML further enriches existing data with the ability to identify patterns, points of interest, and anomalies that previously have been difficult to identify or replicate. The science of accessing the right data sets will augment forecasts and models that can be woven into the decision-making process.

Some examples:

  • AI enables customized, store specific assortment strategies—moving beyond large store classifications and clusters.
  • ML can identify trends and recommend items, layouts, or colors that are more likely to be successful.
  • AI can align historical sales patterns to changing customer behaviors and project future sales.
  • ML can analyze customer shopping patterns, provide product recommendations, and can also anticipate future customer buying behaviors.
  • AI can curate customer reviews, identify trends in customer sentiment, and tell a story around returns and sales data.

These technologies thus enhance the decision-making process rather than replace it, keeping in mind that these tools operate based on the data and parameters provided to them in the data ecosystem. Having the right strategy and infrastructure in place to promote the availability of high-quality, trusted data is imperative.

Without access to the right data, learnings from AI and ML tools won’t provide the support needed to drive crucial insights. Notably, there has been a shift in the ML workflow where the initial step has transitioned from a one-time data preparation activity to a more robust, sustained practice of intentional data management.

Given the criticality of having the right data inputs, an increasing number of organizations are investing in data and analytics platforms and governance models. A mix of data strategy, governance, quality, and architecture are all key components. As AI models continue to mature, the science of recognizing and managing data as a primary contributor will maximize the value of data science initiatives.

The Art: Creating Agility with AI’s Rapid Retail Insights

Witnessing the rapid evolution of today’s consumer behavior, driven by trend dissemination, challenges norms such as traditional seasonal models. Previously, retailers looked to runway shows and high-end brands for style direction that informed seasonal models, resulting in a trickle down of trends from luxury to mainstream markets.

Now, AI and ML can identify shifts faster and earlier, making fast fashion possible - rapidly introducing garments to the market that imitate new trending styles. This shift necessitates retailers to closely monitor micro trends and swiftly adapt assortment and item plans, which is an art in itself.

With access to unprecedented data, the inputs can begin to feel overwhelming. The key has now become employing AI in the retail industry to drive the right insights and creating an agile merchandise planning strategy that gets smarter with every new piece of data. The art of merchandise planning includes understanding what questions to ask and knowing how to strategically direct your AI and manage the data. If done resourcefully and creatively, merchandise planners can build long-range plans that incorporate market direction and reserve the appropriate open to buy for the business.

A Paradigm Evolution, Not a Revolution

 Merchandise planning is evolving into a dynamic fusion of art and science. AI and ML are driving a paradigm evolution rather than a complete revolution. AI and ML don't replace merchants and planners; they augment their decision-making processes. Retailers navigating this dynamic landscape must embrace available tools and technologies while valuing the expertise of seasoned merchandisers.

Moreover, in this evolved landscape, the role of structured data and data management techniques becomes increasingly crucial. AI and ML, when coupled with properly managed data, bring forth new avenues in decision-making for merchants.

With the right data management strategy in place, brands can bridge the gap between insightful data and strategic decisions with AI tools. Whether a brand is just embarking on this journey, or is relooking at their strategy and how to apply AI and ML into their business, a few key considerations should remain front of mind:

  • Set an overarching strategy early and approach AI & ML with specific use cases that serve the needs of the business.
  • AI & ML insights are only as good as the data they learn from -- make sure your data strategy is in sync with the goals of your business.
  • Consider AI & ML as complementary to the tools and brain trust you leverage today.

What to Read Next