2025 Franz Edelman Award finalist: SF Express

Ashley K:

Welcome to the latest in our special series of resoundingly human podcasts, highlighting the finalist teams for the 2025 Franz Aleman Award. The Nobel Prize of Analytics, which will be awarded at the upcoming 2025 INFORMS Analytics plus conference in Indianapolis this April. These finalist projects represent teams from around the world who have leveraged advanced analytics to transform their organizations, address their most significant challenges and better serve their customers and communities. Today I’m joined by members of the team representing SF Express to discuss their finalist project in the lead up to the Franz Edelman competition. Why don’t we start by having you introduce yourselves and share a little bit about your role in the organization and how it relates to this project.

Yixiao Huang:

Hi Ashley. It’s great to meet you. My name is Yixiao Huang, I got my PhD in Management Science from Shanghai University in 2018, and my dissertation was on the optimization of ology systems. So it’s natural for me to join SF Express as an operation researcher trying to apply some of the art techniques I learned. So since joining SF Express, I have worked on the network design project. I was fortunate to participate in this project from the very beginning in 2018. So currently I’m leading an OR team that focuses on network design and operational innovation.

Fei Gao:

Hi Ashley. Thank you for having us here today. My name is Fei Gao and I got my PhD in system engineering and engineering management from City University of Hong Kong in 2018. And in the same year I joined SFX Prize ICE on Operation Research Engineer. In my job, I developed the mathematical models related to network planning and one of the main project I have been working on is designing the inner city air network, which is an important part of this finalist project.

Ashley K:

Could you walk me through the key objectives of your project and why it’s so impactful for SF Express?

Fei Gao:

Sure. As we know that China’s express and delivery industry leads the world in partial volume since 2014. And in 2021 it hit a major milestone with over 1 billion parcels delivered, which is about 70% of the world’s total. And SF expressed as the top integrated logistic provider in China and also in Asia is known for is speed, reliability, and excellent service. And SF Xpr has been ranked in number one in customer satisfaction within China for 15 consecutive years. So behind the SFS operational efficiency is a very complex logistic network. In the past, this network was planned manually by regional planners, but as parcel volume grew, SF needs advanced, the techniques to support this planning and our project aim to reshape this planning procedure at SF xpr. So we focused on reduce the cost enhancing delivery speed and the customer satisfaction. And more importantly, we wanted to reduce the fuel consumption and the carbon emission to make the logistic industry more sustainable.

Yixiao Huang:

And I explain why this project is impactful. I think it’s in several ways. So first we have completed changed the workflow of network planning procedure at SF Express, which improves decision making efficiency. And second, the OR tools we developed have supportable strategic and operational planning. Our network design, including planning SFS new air hub hub, which is very important for sf. And besides this project has resulted in significant benefits. So accumulatively, we have reached a reduced millions of tons of carbon emissions and saved over a billion dollars in costs and decrease deliver time for over a billion parcels. And in addition to this, we also have generated some external influences. We have published standards, patents and academic papers on green logistics and the network optimization techniques, which is helpful for other express companies. And the last impact I want to highlight is our academia. So SF Express once collaborated with Georgia Tech, in the early stages of this project, the OR teams were somehow inexperienced and we were fortunate to receive guidance from the faculty at Georgia Tech. And today we want to return the favor by sharing some of our experience as well. So our team members have given talks at many universities in China, and some of us also serve as part-time lecturers teaching the practical or masters at a university. And additionally, we have hosted several competitions featuring real world optimization problems. We hope these actions will attract more young talent to work in the industry as operations researchers.

Ashley K:

Wow, that’s really impressive. I’d love to know, how did your team balance technical complexity with ensuring the solution was practical and implementable?

Fei Gao:

Sure. First, we had to dive deep into the problem and work closely with the business team. This could ensure that we could truly understand the problem we faced and make sure that our problems are feasible and our solution aligned with the business goals. And given the complexity of the business, sometimes it is very difficult to identify for us to understand all the business constraints. So we started with a small case study and we iterated with the business team refining our approach along the way. This help us gradually build our understanding and the tackle hidden and challenges. Secondly, we select the right technical solution to manage the overall complexity of our project. We adopt some multi-stage approaches. For example, we focused first on optimizing the air network, which is about some strategical results allocation before moving on to the ground and the in city network. And additionally, we incorporated planning experience from the business team to reduce technical complexity in our model and make sure that our solution worked well in the real world. So in summary, we balance the technical complexity by deeply under understanding the problem, collaborating closely with the business team, starting with a small case and iterating, and finally taking a multi-stage approach to tackle the problem systematically.

Ashley K:

In your experience, what makes for a great team working on a high stakes analytics project? How did your team foster collaboration throughout this whole process?

Yixiao Huang:

I think when working on a high stakes analytics project, the most important thing is to make sure that you are solving the right problem. It is the most important one, and it is also important to make a reasonable plan and take small steps to be able to deliver continuously. And also, as you mentioned, I think collaboration is very important as well. I can share some experience related to our team’s collaboration. So at the very beginning of the project, we discovered that the network planning team did not understand the OR techniques and the OR team was not familiar with the business either. So to cope with this challenge in 2019, the OR team joined the network plan team to learn from each other and work together to tackle this problems. So this is an organizational experiment and we believe it had resulted in a virtual circle.

So now both teams can communicate in the same languages, both the OR language and the network planning language. Another thing about collaboration is to activity reach out to other teams. I can share a story from a few years ago when SF initiated a system to track the carbon emissions. So as the OR team, we were excited as we knew when we optimize the network, we also reduced the parcels travel dissonance on average, and the reduction of travel distance leads to the reduction of carbon emissions. We always knew the environmental benefits, but we just couldn’t measure it. So we reached out to the team working on this system and shared our work. So they were excited as well. And we started to work together to track the reduction of carbon emissions from the network design project. Then it turned out to be that we have reduced a lot of carbon emissions for sf. So I think there are many potential opportunities for optimization and you always need to be active to achieve more collaboration, to work on more interesting problems.

Ashley K:

So now that your project has been recognized as a for the Franz Edelman Award, what’s next for your team? Are there future opportunities for scaling or expanding your work?

Fei Gao:

Sure. Being a finalist for the Franz Edelman Award is a huge honor for our team. It validates our hard work and the dedication to using the advanced or technology in logistic industry. So next, our team plans to continue our research on network planning to adapt to changes in the external environment and align with SF strategic goals to generate even more benefits. And additionally, our OR team will also actively look for more opportunities within IF fixed price to apply this or methodologies.

Yixiao Huang:

In addition, we believe there are many future opportunities for expanding our work. So we believe the network structure of SF is quite unique. For example, we operate with multiple shifts within a day. So parcels collected at a different time of the day may follow different routes to their destination with different service levels. We think such a network is feasible due to the high demand density in the Chinese markets. So with the continuous growth of e-commerce, we think more countries and regions will achieve higher demand density. And we anticipate that more express companies will adapt to the SF network structure to deliver, sorry, start again. So we anticipate that more express delivery companies will adapt to the SF network structure to deliver a better customer experience. So this network design project with the publications standards and penance, we have introduced service as a good reference to them.

Ashley K:

And finally, what advice would you give to teams that are just starting out on their analytics journey, especially those that might be aiming for their own Franz Leman award someday?

Yixiao Huang:

Actually, we did propose four suggestions at the conclusion part of our paper. We believe it’s very important, so I’ll introduce them. So first, dive deep into the business and truly understand it. That’s a very important thing when starting a new project. And second, make sure you’re solving the right problem. So make sure the problem is valuable and it is implementable. Then when you know the business and you pick a problem to study, you need to design the algorithms. And it is important to learn from human experience when designing your solution methodology. And the fourth one is for those aiming for the French Edman award, which is perseverance. I think all of the edman finalist teams in history have solved some very complex and challenging optimization problems, which require time and the patience.

Fei Gao:

My advice is to collaborate openly and closely with the professional business team. I think learning from each other can really make a huge difference, especially if you are aiming for the friends atman world.

Ashley K:

I think that is absolutely wonderful advice. Thank you both so much for taking time to share this special insight into your finalist project. I wish you the very, very best of luck in the Franz Edelman award competition. And look forward to meeting you and the rest of your team in person in Indianapolis for the 2025 informs Analytics plus conference.

Yixiao Huang:

Thank you, Ashley. Looking forward to seeing you. Thank you. Thank you.

Ashley K:

If you’d like to learn more about today’s episode and guest, visit resoundingly human.com and check out our show notes. The podcast is also available for streaming and download on Amazon Music, apple Podcasts, Google Podcasts, and Spotify. Wherever you listen, please be sure to leave a five star review to help others find and enjoy the podcast. Until next time, I’m Ashley K and this is Resoundingly Human.