Mastering Retail Merchandise Planning in a Post-Pandemic World

The wind-down of the COVID-19 pandemic in 2022 brought unprecedented shifts in retail industry dynamics worldwide. Traditional forecasting models reliant on historical data were thrown into disarray, making merchandise planning an immensely challenging task. The aftermath of the pandemic world calls for a recalibration of our approach to this critical aspect of retail. In this new world, the role of cutting-edge technologies such as AI in addressing these challenges cannot be overstated.

Challenges in Historical Data Use for Forecasting

Merchandise planning is a foundational pillar for retail success, striking a delicate balance between consumer demand and stock levels. Typically, retail businesses harness historical data to predict future demand. This information guides decisions on what, when, and how much to stock, optimizing sales while minimizing stock holding costs. But the 2020 pandemic has significantly distorted historical data, making it a less reliable predictor of future trends.

For example, during the pandemic, many consumers turned to online shopping, causing a significant boost in e-commerce sales. Retailers dealing in home office equipment, fitness gear, or baking supplies saw an unexpected surge in demand. Contrastingly, sectors like travel retail or formalwear suffered a steep decline. Now, as we firmly transition into the post-pandemic era, the question remains: Were these shifts temporary or permanent?

The answer is complicated – Using 2020 and 2021 data might lead a fitness gear retailer to overstock, expecting similar growth levels. Conversely, a travel retail business might understock, assuming the slump continues. Looking at data from 2023, none of those trends continued in recent years. In fact, in the current post-pandemic environment both scenarios would likely have led to significant financial losses and customer dissatisfaction, emphasizing the challenges of forecasting based on historical data over the last three years.

Strategies to Overcome These Challenges

Fortunately, we can tackle these challenges with a mix of data-driven insights, flexibility, and a customer-centric approach.

Embracing Data Granularity
Looking at sales data at a more granular level can help retailers decipher whether changes in sales are due to external factors or genuine shifts in consumer preferences. For instance, evaluating the data month by month, or even week by week, might reveal trends corresponding to varying historical levels of lockdown restrictions, helping businesses differentiate between pandemic-induced fluctuations and long-term trends.

Diversifying Data Sources
Integrating a variety of data sources can offer a more holistic view of consumer behavior. Besides sales data, consider including external factors like economic indicators, latest changes in demand signals and category based trends from web activity in your forecast model. This strategy could offer insights into how these elements have influenced past sales and how they might shape future demand. The key is to look at leading demand signals from places like Social Media and recent sales in addition to historical data in order to get the most accurate forecast of future demand.

Staying Flexible
Flexibility is key in this uncertain environment. Retailers need to frequently revisit and update their merchandise plans to adjust to changing circumstances. Incorporating flexibility in supply chains through practices like dropshipping, which allows retailers to purchase items from a supplier and have them shipped directly to the customer, can also help manage unpredictability in demand.

The Role of AI in Retail Merchandise Planning
AI-driven retail merchandise planning software can play a significant role in overcoming these challenges. They offer features like machine learning algorithms, predictive analytics, and real-time data processing, providing businesses with a more dynamic and accurate forecast model.

AI can analyze vast, diverse data sources, both historical and real-time, with incredible precision, helping retailers make sense of complex patterns that might be missed by traditional methods. For instance, OmniThink.ai AI-driven demand forecasting software leverages machine learning to consider hundreds of factors, including weather forecasts and social media trends, to generate highly accurate demand predictions.

AI also excels in identifying long-term trends versus temporary shifts. As we discussed earlier with the fitness gear retailer, AI could analyze granular data and detect the trend of sales normalizing as lockdown restrictions eased, indicating that the surge was a temporary shift during 2020-2022.

Additionally, AI software offers adaptability, learning, and improving its predictions over time, crucial for navigating an uncertain post-pandemic retail landscape. Tools like AI merchandise planning software can regularly recalibrate forecast models based on the most recent data, ensuring retailers stay responsive to changes in consumer behavior or external conditions.

The Bottom Line: the post-pandemic world poses unique challenges to merchandise planning. However, by leveraging the power of granular data, diversifying data sources, maintaining flexibility, and harnessing AI technologies, retail businesses can adapt and thrive. The future of retail merchandise planning is undeniably data-driven and technology-centric, with AI leading the charge towards a resilient and dynamic retail landscape.