The solution here aims to use AI/ML models to enhance NBA planning efficiency and effectiveness by leveraging machine learning techniques and comprehensive data analysis, and provide curated recommendation at a monthly/weekly level based on the types of constraints set.
In today's competitive market, achieving optimal Next Best Action (NBA) planning is crucial for maintaining effective engagement with Healthcare Professionals (HCPs). Traditional methods often fail to consider the dynamic nature of HCP preferences and external constraints, leading to suboptimal promotional planning and budget utilization.
Our Omnichannel Prediction Model addresses this challenge by leveraging advanced AI/ML techniques to provide actionable insights and recommendations. By integrating comprehensive data analysis and machine learning models, we enable organizations to:
By implementing this solution, organizations can significantly enhance their NBA planning processes, leading to increased engagement with HCPs, better budget management, and improved overall effectiveness of promotional activities.
Here we have create a ML model, which generates NBA predictions based on the input data and user input contraints from GUI.
There is one Notebook and One Script in the package:
If you are new to Databricks, create an account at: https://databricks.com/try-databricks
Several omnichannel-specific datasets have been used to build and run the model. Sample datasets can be found in the "Data_Files" folder, along with an additional README "Data File Information.png" file containing data specifications.
© 2024 Databricks, Inc. All rights reserved. The source in this notebook is provided subject to the Databricks License [https://databricks.com/db-license]. All included or referenced third party libraries are subject to the licenses set forth below.
Library | Description | License | Source |
---|---|---|---|
pandas | Data manipulation and analysis | BSD 3-Clause | https://github.com/pandas-dev/pandas |
numpy | Numerical computing tools | BSD 3-Clause | https://github.com/numpy/numpy |
scikit-learn | Machine learning library | BSD 3-Clause | https://github.com/scikit-learn/scikit-learn |
gekko | Optimization suite | MIT | https://github.com/BYU-PRISM/GEKKO |
joblib | Serialization and deserialization | BSD 3-Clause | https://github.com/joblib/joblib |
pyyaml | YAML parsing and writing | MIT | https://github.com/yaml/pyyaml |
plotly | Interactive plotting library | MIT | https://github.com/plotly/plotly.py |
matplotlib | Static plotting library | Matplotlib License | https://github.com/matplotlib/matplotlib |
mlflow | Machine learning lifecycle management | Apache 2.0 | https://github.com/mlflow/mlflow |