This website uses cookies primarily for visitor analytics. Certain pages will ask you to fill in contact details to receive additional information. On these pages you have the option of having the site log your details for future visits. Indicating you want the site to remember your details will place a cookie on your device. To view our full cookie policy, please click here. You can also view it at any time by going to our Contact Us page.

Gaining a deeper supply chain understanding

10 January 2022

Kimberly Carey Coffin discusses how the rise of big data and AI is already having a powerful effect on how food supply chains are managed, and what needs to be considered going forward. 



Continue reading this article

Register now for free and access every article and to register for the print edition.




With copious amounts of data amassed each day, food manufacturers must learn how best to use this to identify risks. 

The volume of data produced and collected every day across all industries is immense. For those in the food manufacturing industry, the challenge is knowing how best to use that data to understand the true risks to product integrity. However, as organisations try to balance many competing priorities, technical teams are often stretched to the limits. Therefore, finding better ways to use technology to leverage data is key for a more targeted effort into mitigating areas of highest risk.

Start with the problem
When looking to gain deeper risk insight, many organisations start by focusing on the right technology solution or by employing data scientists, rather than identifying the problem they are trying to solve. By taking this approach, the project is often focused on the data and not on the desired insight the technical teams are seeking.

Identifying the problem first will allow organisations to make better data-driven decisions. An example of which would be the highest risk suppliers in their network and the dynamic risk factors contributing to that risk score. By finding this, it is possible to identify the specific data sources as well as helping to map the journey of those data sources through the organisation.

Understanding data
From both internal and external sources, the quantity of data generated by individual companies is substantial and often disparate. As such, the challenge for businesses is often how this is combined in an efficient manner to create a true picture of the most significant risks to product integrity. This is where the application of AI – underpinned by a sound risk taxonomy – comes to the fore. Through the design and application of layered taxonomy, identifying where to focus risk mitigation efforts and intervention becomes more straight forward.

AI has often been used to gain greater insight into shopper habits and new product development. However, its application for establishing transparency of supply to mitigate product risk is still a relatively new proposition. Increasingly, companies are asking about how they can utilise data from product recalls, as well as their own internal product failure and supply network audits, to give them an edge when it comes to identifying and predicting future risk.

It is important to remember that human technical analysis goes hand-in-hand with the application of technology, when setting out to make sense of data and identify critical risk factors. The recommendation to companies is to find the right balance between food science and data science when considering how best to make sense of data.  Keeping a human in the loop is essential to improving the accuracy of Natural Language Processing (NLP) and machine learning models and to build confidence in the resulting insights these models provide.

Using technology to get deeper insight into areas of critical risk from data is just the start. Those insights must translate into actions that make a difference, enabling technical teams to focus their effort on those areas of most significant risk impact by actioning targeted interventions that drive improvement.

Building trust
Given that transparency of critical supply risks using a company’s own data has its limits, a collaborative approach among industry stakeholders is a necessity. Unfortunately, there is some reluctance to open trusted networks. Yet to obtain complete transparency, the sharing of data and information between businesses and along the supply chain is crucial. 

As we move towards a digitally-enabled future, there are risks to be considered. Adopting digital processes leaves the door open for potential data theft across the supply chain, putting product integrity at risk and elevating chances of fraud and product recalls. This means organisations must seriously consider how they can build confidence that they are protected from a potential attack; what recovery plans are in place in case of an attack; and how prepared third-party suppliers are, if transparency of risk is to be achieved.

Through the adoption of new technology, businesses are able to harness the power of data and learn how to best understand product and supply network risk. It is through gaining this greater intelligence, insight and predictive capabilities they can make necessary improvements in systems and processes to proactively mitigate risks, rather than reacting to individual risk events and incidents. In order to gain an even deeper understanding of their supply chain, data management and sharing amongst all stakeholders through both blockchain and AI will be fundamental. This will allow manufacturers to form more informed decisions. However, for a digital future to be fully realised, there needs to be recognition of the importance of shared data. No one business can do this alone, and there needs to be shared responsibility to create a transparent, end-to-end food supply network built on the strength of risk data. 

Kimberly Carey Coffin is global technical director at LRQA.


Contact Details and Archive...

Print this page | E-mail this page