Top 5 opportunities for applying data-driven continuous improvement in logistics
There is a big trend and focus on becoming data-driven and applying AI within organizations. Often, a natural starting point is the implementation of software solutions that support primary processes: such solutions create a valuable data lake containing important and relevant planned and actual information. But that’s just the very beginning of getting value out of data in a continuous way.
This article is powered by Goos Kant, Professor Logistic Optimization Tilburg University and Managing Partner ORTEC
Applications that facilitate action
It’s all about the value hidden inside the data, not about the data itself. Therefore, the next step is to create applications that work with this data. For instance, by applying R or Python and showing the data in a dashboard. Typically, all this is done by a data science team within the company, supported by business experts, to store and show the right KPIs and other information. This team plays an important role in supporting the business with the right insights, which often leads to more clarity for what concerns the company’s current situation and goals. However, it often makes sense to generate these insights only if the business is actually willing to take actions based on the recommendations.
Top 5 opportunities in logistics
Within logistics, there are various opportunities for continuous improvement of the business, based on the data-driven approach described above. Here are our top 5 most recognized opportunities in practice:
- Performance Analysis: What is the daily status of the most important KPIs? What are the top 5 contributors and the worst 5 performances? Are there ways to clarify the changes? How was the usage of the system itself, are there ways to further automate processes to avoid human mistakes?
- Planned versus Actual: what is the difference between the planned and actual schedule in logistics? Can this information be stored, analyzed, and used to improve the next forecast? Note that reducing the gap between planned and actuals by applying self-learning techniques improves both the reliability and the efficiency of a plan.
- Forecasting volume and assets: Based on historical data and future trends, it is possible to predict the expected volume for the coming period in a much more accurate way. Based on this volume, the right resource mix (like assets and fleet mix) and required workforce can be estimated.
- Deployment of employees: was the employee roster feasible and efficient? Did it respect the labor rules and personal wishes? And did we make the right choices when hiring sub-contractors? What would be the ideal workforce mix for the coming period? Which capabilities do we need?
- Delivery performance: when allocating all activities through a (machine-learning powered) cost-to-serve model, good insights can be obtained per contract, and per delivery address. Comparing this with the revenues and contract details gives a good insight in the P&L per supplier and/or receiver. It also helps to reflect the contract conditions, which is in turn helpful in negotiations and tendering support.
The big question
The big question is: “How do you establish continuous improvement within your organization?” To answer this question, we have created a webpage with cases, videos, and best practices to help you take the next steps, like:
- Show that the leadership trusts data and its capabilities for continuous improvement.
- Create a (young) diverse data science team with the right knowledges to challenge the business.
- Create a winning environment: measure the results and celebrate the successes.
- Keep focusing on impact and benefits, rather than on techniques and insights.
What’s your experience?
I am also curious about your experiences and feedback. Let’s connect, so that we can learn from each other to make our world (a little) better.
About the author
Goos Kant (1967) is a full-time professor of Logistic Optimization at Tilburg University. He is involved in the master program of Business Analytics and Operations Research, as well as in the master program Data Science & Entrepreneurship. He is the project leader of a large R&D project on horizontal collaboration in logistics. Goos is also a managing partner at ORTEC, with global responsibility for all solutions in the logistics industry. His primary area of interest lies in the 3PL-industry in optimizing their planning processes in the end-to-end supply chain. Goos is involved in courses from MBA-schools TIAS and Nyenrode. He holds both an MSc and a PhD in Computer Science.
