Client's Challenge:
PSW, Pedagogisch Sociaal Netwerk, is a Dutch care institution that focuses on providing day care and assisted living for people with disabilities. For PSW, wages are their biggest expense. Therefor the more efficiently they can schedule their employees, the better. Currently, the organization schedules its staff depending on the number of clients registered for day care. However, some of the clients do not show up for day care when they are planned in. This due to external factors such as the weather, travel distance or others. By using machine learning we were able to make a prediction of the number of clients that would effectively show up for day care.
Our Solution:
The solution has been built based on the data science lifecycle approach, where data analytics, data clearing creating a proof of concept (POC) and deploying the solution, have been key components. During the proof of concept development phase, several algorithms were tested, trained, tuned, and compared to select the best possible foundation. A machine learning approach was employed to automate the experimentation process. The PSW in-house experts handled the analysis and preparation stages. In the deployment phase, the model was deployed as a service. This deployment strategy ensured the model’s accessibility and integration into the existing infrastructure, enhancing the decision-making process for the client.
Created Impact:
Our solution optimized employee scheduling and reduced costs in the daycare department. By accurately predicting client attendance, staffing levels were efficiently planned, resulting in improved efficiency. This implementation showcased the power of machine learning in enhancing resource allocation and operational efficiency for care institutions.
