Real-Time Predictive Analytics for Prescription Deliveries

Objective​

Predict whether a prescription delivery would be late or not, and if it would be late what would be the reasons behind it being late. The client requested us to make it as easily understandable as possible.​

Industry: Healthcare​

Technology: Microsoft Fabric, Power BI, EventHouse, One Lake, Dataflow, Azure ML, Azure SQl Storage, Python, MLFlow, PySpark, Scikit-Learn​

Goals​

• The client required a solution to predict whether prescription deliveries would be delayed and understand the reasons behind such delays in a clear manner. ​
• They wanted real-time updates on the status of deliveries and insights that were user-friendly and visually appealing. ​
• The solution needed to be scalable, adaptable, and capable of handling increasing data complexity while integrating seamlessly with existing data sources like Azure SQL Storage. ​
• A continuous learning capability was essential to enhance the model's accuracy over time and adapt to new data effectively.​

Our Solution​

• Created a solution utilizing Microsoft Fabric services like Lakehouses, Dataflows, Notebooks and Reports.​
• Utilized ML models made using MLflow experiments and PySpark to predict the probability of the delivery being late. ​
• Implemented model explanation algorithms to let us interpret the reasons behind a specific delivery being.​
• Created Active Learning pipeline within Fabric to continuously train the model as ensuring that the model would improve over time.​
• Power BI report to visualize the results & monitor the accuracy of the model and summarize historical data.​
• Utilized Dataflow Gen 2 pipelines to transform data at various stages of the solution.​

Business Value​

• Using the solution the client was able to figure out the main reasons behind the prescription deliveries being late in the past as well as the future.​
• The visually appealing Power BI report let the client be able to learn about the most important decision factors and look at the changes in them with each delivery. ​
• It enabled him to expand the business, enhance operational effectiveness, and achieve high levels of customer satisfaction.​