's Sybilla – Demand Forecasting's Sybilla – Demand Forecasting

Sybilla –'s demand forecasting tool helps analyze sales data and predict future demand to optimize logistics, supply and stock costs . Demand and sales forecasting is a crucial part of any business. Traditionally it has been done by experts, based on know-how honed through experience. With the power of machine learning it is now possible to combine the astonishing scale of big data with the precision and cunning of a machine-learning model. Sybilla uses machine learning to predict demand daily sales of products across multiple shops. Deepsense made this possible with XGBoost and LightGBM Libraries and optimizing on Intel helped them reduce training time and crunch huge volume of data on Intel Xeon Scalable Processors

*Please note that member solutions are often customizable to meet the needs of individual enterprise end users.



  • Loss Reduction
    Sybilla helps in analysis of loss reduction . Any demand that was not fulfilled should be considered a loss. Moreover, the company freezes its cash in stock, thus reducing liquidity.
  • Supply Chain Optimization
    The bigger the organization, the more sophisticated and complicated its inventory management must be. When demand is forecasted precisely, managing and estimating costs is easier
  • Better Marketing and Sales Management
    Depending on the upcoming demand for particular goods, sales and marketing teams can shift their efforts to support cross- and upselling of complementary products
  • Supporting Expert Knowledge
    Models can be designed to build predictions for every single product, regardless of how many there are.


WorldwideBrazilFranceGermanyIndiaJapanKoreaMainland ChinaMexicoOther - Asia PacificOther - Europe and AfricaOther - North and South AmericaTaiwanUnited KingdomUnited StatesAI Software/SaaSRetailData AnalyticsData Preparations and ManagementCSP - Amazon Web ServicesCSP - Google CloudCSP - Microsoft AzureCSP - OtherHybrid CloudOn-premise (Private Cloud, Other)Intel® Xeon® Scalable ProcessorModels can be trained - requires labeled dataLinux OtherDeep Learning