About the Customer:
“Darnytsia” is the largest Ukraine-based pharmaceutical company with a rich history spanning over 90 years. Renowned for its leading position in the domestic market, the company consistently demonstrates excellence in production volume and industry rankings. Darnytsia is also recognized for its successful digital transformation and innovations in the pharmaceutical field.
Executive Summary
Goal: Our client aimed to improve business productivity and resource planning with accurate multidimensional sales predictions for an 18-month period.
Solution: Implemented an ML-based sales forecasting solution with 95% or higher accuracy across four dimensions (‘Total Market’, ‘Drug Categories’, ‘Top 10 Drug Producers’, and ‘Competitive Drug Groups’).
Benefits: Optimized resource planning, drug supply & logistics, reduced operational costs, faster decision-making, enhanced customer service, higher competitiveness, and stronger position on the market.
Services delivered: Innovation Services, Intelligent Business, AI/ML services, Predictive Analytics, BI & Data Analytics, and Advanced Analytics.
Business Challenge
After a successfully delivered data analytics bot project and other solutions and services, Infopulse was contacted by Darnytsia to develop a sales forecasting solution to generate accurate sales predictions.
The project involved a range of severe challenges:
- Highly volatile market: Darnytsia operates on the Ukrainian market, which is extremely volatile due to war against russia, economic instability, and unpredictable population migrations from region to region or abroad.
- Pharmaceutical business specificity: In a very short timeframe, we had to understand the business specifics to select suitable data models and consider all the factors that affect drug sales.
- Short Deadline: The solution had to be delivered in less than a week, as the company wanted to present it to the board of directors.
Infopulse decided to take these risks and implement the requested solution.
Solution & Business Value
Infopulse team developed a sales forecasting solutionthat generates sales predictions for an18-month period with an error margin of less than 5%.
The business gains brought to Darnytsia include:
- Better sales planning: 95% or higher accuracy in sales helps minimize stockout risks
- Better production and supply planning: understanding the required product volumes for sales helps adequately adjust the production and resources.
- Enhanced cost-efficiency of operations and logistics
- Enhanced level of service: significantly lower risks of underproduction or stockout.
- Faster time-to-insights for efficient decision-making for proactive business strategy development
Technical Details
The project had an extremely tight deadline – only a couple of days for the initial scope of the project. We started with processing data received from Darnytsia to merge available drug tables and sales data for the modeling process.
In parallel, we were doing research to select models and solutions that effectively work with sales predictions. Two potential methods were selected for modeling:
- Temporal Fusion Transformer (TFT) — a very sophisticated Deep Learning model for time series forecasting. It works pretty well with big and complex time series for different categories.
- Prophet model — a forecasting model for time series data implemented in R and Python. It is one of the open-source tools by Facebook widely used by businesses to predict the market, based on more low-level methods (autocorrelations, classic time series forecasting theory) compared to TFT. Nevertheless, it is powerful enough to produce accurate market predictions in certain cases.
We needed to correctly put the data into the chosen models, obtain the forecast, and evaluate the accuracy. Thus, we cut the last 12 months of the available history data and treated them as an evaluation period.
Next, we worked on improving the models. After testing numerous approaches, we selected three improvements that helped maximize the accuracy of sales predictions:
- Hierarchical forecasting: We predict the behavior of the high-level drug group by forecasting low-level subcategories and summarizing the results into a high-level group prediction.
- Switching from absolute mode to relative: On an absolute scale, we just had the volume of drugs sold in a particular month. On a relative scale, we switched to comparing the difference to the previous month. We got the base level of sales and then applied the growth rate month by month. By applying relative valuations, we managed to address migrations and other seasonal changes typical for the target market.
- Switching from the average volume per month to an average volume per day for each month: As each month has a different number of days, predicting the average daily volume gave an additional decrease in total error for the forecast.
We also implemented specific holiday indicators in time series to indicate events and special months the model needs to treat differently.
By implementing these improvements, we finally got the results of less than 5% total error for 18-month predictions.
Upon testing both models, the Prophet model was
selected as more suitable considering the deadline. In addition, Prophet showed
slightly better accuracy (4-5% total errors compared to 6-7% total errors in
TFT) yet TFT was significantly more complex in handling and adjustment. The
time series didn’t require such complexity of processing, and there was no
reason to invest additional effort in using TFT.
As agreed, initially we created predictions for two of the four required dimensions — ‘Total Market’ and ‘Top 10 Drug Producers’. Over the following week, we implemented 18-month predictions for ‘Drug Categories’ (15 categories in total) and ‘Groups of Competitive Drugs’.
Serhii Kolchyk
Technologies
Related Services
We have a solution to your needs. Just send us a message, and our experts will follow up with you asap.
Thank you!
We have received your request and will contact you back soon.