Data analysis helped pharma company bring down production costs

About client

The client is a leading pharma company, which manufactures vaccines like DTP. They have production plants in multiple global locations. They have highly compliant production spaces, modern labs, and well-planned production cycles to maintain product and batch consistency and stay in line with compliance requirements.

Challenges

The client faced the following issues with their current vaccine manufacturing process, which is highly regulated.

Increasing manufacturing costs: They noticed that their current production costs are increasing and uncontrollable, especially with night shifts. Besides, operational inefficiencies further increased production costs as they addressed defective batches, which hiked their resolving costs to 207%. The production cost also varied across their different locations which required deriving location-wise efficiency.

They also wanted to narrow down on production costs further, trying to correlate manpower and shift costs, and how the work timings impact the expenses.

Consistency issues across locations: Every location produced goods at different quantity, expenses, and efficiency.

Batch rejections: They noticed an increased number of batch rejections due to various reasons, especially their rejection cost for a specific vaccine was higher than 120% due to reasons like batch ineffectiveness and expiration. This impacted their manufacturing standards, production output, and manufacturing and supply-chain expenses.

Proportional inefficiencies: They require in-depth proportional analysis to identify and address areas of improvement in problematic categories like production costs, rejections, manpower, production time, and resolving costs.

Every above issue related to operational inefficiencies required careful data analysis and a comprehensive monitoring system.

datakulture Solution

Our team established a real-time cost and production monitoring system that helped them get insights into manufacturing whenever required.

Production cost monitoring: Our team set up descriptive analytics dashboards that shared details of different vaccine production costs. This helped the company identify high-cost products and optimize resource allocation.

The cost analysis was also done based on shifts and locations. This highlighted which shift is causing more cost implications, leading to a more optimally distributed manpower. By performing location-based production cost analysis, they could find units with high manufacturing costs and low throughput and focus specifically on that.

Rejection monitoring: Looking into rejections based on reasons like packing defects, expiration dates, not meeting standards, leakages, etc., helped them resolve long-term issues and make process-level modifications.

Proportional and what-if analysis: A detailed proportional analysis as they expected to monitor production & resolving costs, involved manpower, production time, etc., for them to find out the most expensive categories. We also created a simulation model that showed how changes in production efficiency could impact cost reduction, so the company can uncover and focus on areas of improvement.

The Impact the above solution created

• 21% reduction in overall production costs by reducing manpower and shift related expenses and 15% of night shift related expenses.

• 25% reduction in resolving costs, due to the proactive defect tracking and monitoring throughout the production cycle.

• What-if analysis improved production efficiency to 55%, which led to more equally distributed workloads and cost savings.

• Reduced batch rejection costs by up to 31% through continuous monitoring, leading to reduced wastage and cost savings.

Conclusion

Through real-time data analysis, we helped our client uncover cost wastage across different categories and bring them down all together. Through optimal resource distribution and manpower allocation, they increased their production throughput while maintaining quality standards and meet manufacturing targets of the day and period. That’s how data-driven processes empowered a healthcare company to make data-driven decisions and implement corrective actions on time to fix their operational bottlenecks.