‘Traditional market growth tactics no longer suffice’

Inconsistent data is a problem that is well-known to many online sellers, especially when selling on multiple channels. Additionally, demand fluctuates, which makes it hard for retailers to implement accurate forecasting. “Traditional forecasting methods struggle in today’s omnichannel retail environment, because they are designed for a stable, linear retail model that no longer exists”, according to Alexey Spas, CEO and founder of software engineering company Instinctools.

Online sales happen on multiple channels

According to recent research, marketplaces accounted for 61 percent of total ecommerce GMV in Europe in 2025. As 47 percent of consumers start their product search on marketplaces, it is not surprising that many online retailers are active on these platforms. New marketplaces keep coming into the market, like the recent launch of the Argos marketplace.

A report in 2025 indicated that most online sellers are actually active on six marketplaces. This makes keeping track of demand, stock levels and sales complex. “Retailers today are navigating a ‘perfect storm’ of market conditions where traditional growth tactics no longer suffice”, says Alexey Spas, CEO and founder of Instinctools, which makes software solutions for retailers, ecommerce, as well as logistics, supply chain and manufacturing industries.

Data-related challenges

“The complexities these industries face extend beyond simple logistics, into technological and data-related challenges.” According to Instinctools, data is frequently scattered across different teams, or isolated systems, which makes it almost impossible to run a unified online strategy. Another challenge is demand volatility and short-lived trends, as well as supply chain disruptions, and promotions that distort normal demand.

‘Traditional forecasting methods like spreadsheets can become a bottleneck for online sellers’

Because of this, traditional forecasting methods like spreadsheets can become a bottleneck for online sellers. This often happens when they are dealing with too many SKUs, channels, markets or warehouses. Manual consolidation or conflicting spreadsheet versions can also become an issue, just as recurring stockouts or excess inventory.

AI-based forecasting models can save time

Forecasting can then take days for online sellers, rather than hours. “This is when retailers typically start looking for tools that can process larger, diverse datasets. AI or machine learning models can combine historical and real-time signals, while also detecting nonlinear relationships and adapting to changing patterns. These models can generate predictions on SKU-, location- or channel-level.”

‘One of our clients implemented AI tools for data quality checks, which reduced time required by 60%’

Instinctools’s software includes AI and ML facilities, though the company does point out that human-led data engineering is still necessary. “But AI can significantly accelerate the preparation phase. One of our clients implemented AI tools for data quality checks, mapping and cleansing. This reduced the time required for these tasks by 60 percent.”