Results
New capabilities and business value through innovative algorithms and data.
The platform that was developed created the conditions for new business opportunities based on innovative machine learning algorithms and operations management, enabling the entry of new players—providers of big data analytics, machine learning algorithm services, and programming—into the traditional methodological framework of supply chain management, making all of the above significantly more competitive.
The new business opportunities that emerged were grouped as follows:
1. Electronic repository of machine learning algorithms
This served as the foundation for introducing the use of machine learning algorithms by supply chain stakeholders, enabling optimal planning of their operations and increasing their competitiveness.
2. Collection and management of independent variable data
Real-time sales data obtained from POS systems and electronic sales platforms (e-shops, e-commerce) were stored not only on the server but also in the businesses’ ERP/WMS/e-shop/e-commerce data management systems, allowing integration with multiple independent data collection interfaces.
In addition, the stored data were automatically processed according to classical preprocessing principles and made available for delivery to external systems upon request in a simple and straightforward way.
3. Dynamic demand forecasting
Demand forecasting was carried out for very short time horizons—even daily or hourly—through the dynamic forecasting system, which was fed real-time independent variable data.
Dynamic forecasts resulted in:
(i) increased prediction accuracy and lower safety stock levels,
(ii) higher probability of accurately estimating urgent orders and a reduction in routes with low vehicle load factors,
(iii) improved service to end customers.
4. Quantification of the added value of dynamic forecasting
The development of the added-value quantification platform enabled businesses to assess the impact of dynamic demand outcomes on transportation, routing, delivery, and inventory management costs, using advanced routing and inventory models that leveraged dynamic demand data.
With the creation and commercial exploitation of the platform, new job positions were formed in supply chain management and in sales, where knowledge of big data analytics and demand forecasting systems was required.
This opened the path for long-term utilization of the country’s highly skilled workforce, which could potentially also access foreign markets to leverage its specialized expertise.
The conditions created by the COVID-19 pandemic contributed significantly, as they led to a dramatic increase in online sales and created heightened demand for experienced personnel in the management of online stores, where dynamic demand forecasting models were applied.
The innovation of the project lies in the fact that it provided a particularly strong competitive advantage within the portfolio of products and services offered by an IT company with clients in logistics and e-commerce, increasing the likelihood of selling the service either as part of a combined package or as a standalone solution.
With the possibility of offering the platform as SaaS (Software as a Service), its use became feasible for small, medium, and large enterprises, covering the full range of potential customers.
Regarding the project’s societal impact, beyond the increase in employment of specialized workforce, its contribution was significant in improving the efficiency of business operations.
This led to more sustainable production, savings in raw materials, and more efficient use of transportation resources, ultimately reducing CO₂ emissions.