Mi9 Retail introduces AI-based demand management solutions

21 December 2018 (Last Updated December 21st, 2018 13:27)

Omnichannel retail solution provider Mi9 Retail has introduced new artificial intelligence (AI) and prescriptive analytics enhancements to its demand management solutions.

Omnichannel retail solution provider Mi9 Retail has introduced new artificial intelligence (AI) and prescriptive analytics enhancements to its demand management solutions.

The new updates featured include demand transference, adaptive allocations, enhanced shape forecasting, and Monte Carlo simulation re-trend.

They are designed to assist retailers in optimising merchandise-planning effectiveness by automating their processes.

Mi9 Retail CEO Neil Moses said: “By incorporating the latest science and innovation into our demand management solutions, we’re giving retailers the ability to optimise their inventory more effectively and efficiently than ever before.

“We are deploying advanced technologies against real-world challenges that impact retailers’ bottom lines.

“We’re giving retailers the ability to optimise their inventory more effectively and efficiently than ever before.”

“Our integrated planning, allocation and replenishment systems are helping some of the largest and best-known brands in the world increase their margins by continuing to improve the overall efficiency of their supply chains.”

The demand transference feature allows retailers to predict and supply locations based on expected fulfilment using the data from omnichannel buying patterns.

Leveraging these fulfilment projections, the inventory planning and allocation solutions can create AI-enabled order recommendations for business growth across the selling platform.

The adaptive allocations feature assists retailers by creating localised assortments using AI.

Retailers can use the new shape forecasting feature to remove the curve from a product’s sales history before regular forecasting and reapplying it to the result.

The Monte Carlo re-trend mechanism uses random sampling and statistical analysis of sample results to self-correct the demand signal to manage product allocation.