Experience next-gen demand planning with Flowlity & AI

New product planning is challenging because there is little or no sales history. Flowlity addresses this challenge by combining human expertise and artificial intelligence. The solution allows the use of analogous (substitute) products or market data to build an initial demand forecast for a new product. Furthermore, Flowlity provides forecasts even for references with very little history by relying on intelligent algorithms capable of generating trends from partial information. Concretely, the planner can manually adjust the initial demand assumptions for a new product in Flowlity (for example, based on the launch of a similar product), then the AI refines these forecasts on the fly as soon as the first actual sales data arrives. This hybrid approach ensures that new product launches are taken into account in the supply plan, avoiding stockouts during launch while avoiding overstocking a product whose success is still uncertain. Flowlity therefore ensures agile planning of new products, highly appreciated in retail as well as in B2B trading where range renewals are frequent.

The quality of historical data is a key factor for reliable forecasts. Flowlity therefore offers a data cleaning process upstream of modeling. Concretely, this involves identifying and correcting anomalies in your sales or consumption history. For example, we detect outliers (an exceptional sales spike due to a promotion or an input bug), missing or inconsistent periods, and we handle them appropriately. Cleaning involves several steps: standardizing units and formats, removing or smoothing outliers, and imputing missing data if necessary. As a general approach to data cleaning describes, it involves "identifying and correcting errors, filling in missing values, and putting the data into a consistent format" before analysis. To do this, Flowlity uses business rules (e.g., ignoring zero sales during a factory shutdown) and algorithms: for example, a statistical method can replace an abnormal peak with a value more representative of the trend. Furthermore, our demand forecasting AI is capable of integrating external data (market trends, weather, etc.) and detecting breaks in the history to avoid biasing forecasts. In practice, during onboarding, our teams assist you in auditing your history: we identify unreliable data with you (for example, a reference whose coding changed during the year) in order to adjust or exclude it. This cleansing phase ensures that the forecasting model is working on a sound basis. Finally, since Flowlity is a learning solution, the cleansing is continuous: over time, the algorithm learns new behaviors and can rule out future anomalies on its own. You will of course retain control over validating or adjusting any processing of historical data.

Yes, these elements are an integral part of the data taken into account. Flowlity allows you to configure supplier calendars, i.e., your partners' working/non-working days. For example, if a supplier is closed in August or only delivers from Monday to Thursday, the supply plan will automatically take this into account: no deliveries will be scheduled outside of their time slots. This avoids unnecessary overstocking or waiting for impossible deliveries. Similarly, the solution manages product launch and end-of-life dates. Our algorithms integrate the item lifecycle: you can indicate that a new product starts on a certain date (with a possible ramp-up profile) or that an existing reference will be obsolete from a certain date. Flowlity “tracks product lifecycles (new products, end of life, etc.)” and adapts forecasts and recommendations accordingly. For example, as an end-of-life approaches, the tool will gradually reduce replenishment proposals and then stop generating them beyond the end date, to avoid unsold items. Conversely, during a launch, Flowlity can use analogies (similar products) or market data to initialize the forecast, so as not to start from scratch. In short, calendar constraints – whether they come from suppliers or your product cycle – are well managed by Flowlity. This ensures realistic planning aligned with operational realities.

Yes, Flowlity integrates promotion planning into its demand forecasting capabilities. The solution allows you to take into account increases in demand related to promotional campaigns or price changes, in order to adjust forecasts and inventory accordingly. You can enter upcoming promotional events (sales, promotions, sales operations) so that Flowlity's AI can anticipate increased demand and offer tailored sourcing recommendations. This allows supply chain managers in retail and B2B distribution to ensure that inventory levels are optimized to meet promotional sales peaks without creating excess inventory after the fact. Flowlity helps avoid stockouts during promotions while limiting post-event overstocks, which improves product availability and customer service rates during these critical periods. (To find out how Flowlity can adapt to your promotional specifics, please request a personalized demo.)

Yes: calendars (working/closing days of suppliers) can be configured, and the start/end of life dates of the products are taken into account to activate or deactivate the supply recommendations for these references. These technical parameters are configured once in the system and are then automatically taken into account by the algorithm during the calculation of needs.

‍