How predictive analytics can boost pharmaceutical manufacturing
New technologies are changing the way pharmaceutical supply chains operate. Here, Marc Herlant, Arthur D. Little, discusses how predictive analytics offers pharmaceutical manufacturers new supply chain capabilities.
The pharmaceutical industry has been changing rapidly, with changes to distribution and drug consumption models driven by new business avenues around individualised medicine, combination therapies, drug and device convergence, and other exciting developments. These, combined with advanced data analytics solutions, are making treatment more effective and affordable and less intrusive, while enhancing quality of life. However, with all these positive changes come challenges for the supply chain. So how can organisations manage the increased complexity in the supply chain to make improvements work for patients and caregivers?
Establishing new supply chain methods
Supply chain imperatives are evolving, from drug production and delivery that are limited in scope towards a versatile supply chain addressing the needs of multiple stakeholders. The traditional supply chain approach based on materials requirement planning has progressed to its limits.
From the patient perspective, the current supply chain creates frustration and complications in individualised treatments, or even fails to offer satisfactory performance with new treatment types. As new treatments become available, new types of supply chains need to be established, with new actors, as well as new technological and logistical systems. Managing these new treatments with traditional supply chain methods is costly and complex, with high risk of non-compliance. Yet, while creating new challenges in terms of regulatory compliance and scaling, the incorporation of these players also provides opportunities in terms of data collection for predictive analytics.
The challenge for companies is to develop new capabilities by identifying useful and necessary initiatives, without putting the ongoing operations at risk by building service models on the basis of correlations that will not be sustainable in the future. The intelligent supply chain, based on predictive analytics and machine learning, is better at demand anticipation (SKU, quantity) and characterisation (localisation, service levels) by identifying and understanding the patterns influencing it, rather than projecting past demand. However, seeing patterns is not sufficient; understanding the “why” behind them is key.
Identifying the predictive value
Moving beyond the world of descriptive statistics, which relies mainly on the extrapolation and (often poor) observation of recurring patterns, companies are entering the domain of predictive analytics, which requires deep data analysis to understand causal links. Leveraging those links, predictive analytics will be able to predict potential states. The complexity of such models is to identify and select the links with predictive value.
At Arthur D. Little we’ve developed a maturity model to evaluate the current situation and development priorities in the supply chain. This methodology allows thorough testing and leveraging of existing analytics pilots to outline key causal factors to integrate into the predictive supply chain:
- Better understand methodologies applied to various pilots, confirm their underlying hypotheses, and identify other available options.
- Pilot methodologies need to be tested on historical company data, and their results compared to actual history, in order to exclude most of the “false positive” methodologies and identify repeated correlations. Those methodologies should be tested in an exhaustive, systematic and automated manner.
- At this step, the correlations have proved to be resilient over time; hence, causality can be assumed, but is not yet proven. A qualitative assessment of the repeated correlations is the best way to identify meaningful and useful causality links.
- Ultimately, the stability of the methodology is pressure-tested, applying “derived laws” in Step 3 against all possible future scenarios to evaluate maximum variability and their implications.
Conclusion
In spite of being a nascent technology, predictive analytics is a top priority for healthcare supply chain executives. Companies need to reflect on how to minimise risks linked to predictive analytics initiatives. Combining the above model with analytical methodology provides a concrete starting point for leaders who want to develop new capabilities in the supply chain.