O2O Demand Forecasting @ISF2026, Montreal

My first International Symposium of Forecasting, a.k.a. ISF, was in Rotterdam in 2014, when I made a presentation about Global Energy Forecasting Competitions. I loved the conference and community, so I came back to ISF2015 in Riverside, CA, and the following year in Santander, Spain. Since 2014, I have attended every ISF except the one in Oxford due to COVID. I was elected as a director of International Institute of Forecasters in 2017, and re-elected in 2021. I co-chaired the ISF2025 in Beijing, right after the end of my second (and last) term. 

During past 9 years, I was involved more as an organizer than a conference attendee. My attention was mostly on how well the conference was run, how coherent the program was, and how to better serve the members of IIF. As the premier conference in forecasting, ISF only allows a speaker to make one presentation. I did not really put in too many thoughts about the one and only presentation I can give at ISF. Of course, I chose the easiest route, presenting an energy forecasting talk every time. 

This year, I realized that I now had an opportunity to enjoy ISF as an attendee. Maybe I should try something different for my conference talk. Well, I did. I picked a topic in online take-out food delivery: A three-level hierarchy for O2O demand forecasting. It's based on a paper recently accepted by the International Journal of Forecasting. 

Our IJF paper should be online soon, but I want to share some takeaways outside the paper, which might be beneficial to the forecasters from other fields.

1. It takes some courage to break the status quo.

This IJF paper was related to hierarchical forecasting of online to offline takeout food delivery demand. The original ask was just to develop the forecasts, which could have been done simply by using some off-the-shelf software packages. However, we quickly found out that the existing hierarchy was not optimal for neither business management nor hierarchical forecasting. We then took a detour to investigate the methodologies to construct the hierarchy, which eventually turned into this paper. 

2. The same idea can be applied to seemingly different applications and industries

The core idea of this IJF paper was originally from my master thesis back in 2008. It was later adopted by my wife in her doctoral dissertation in 2010. My master thesis was on electric load forecasting, while her dissertation was on supply chain. The O2O forecasting problem did not even exist at that time! Sometimes we just need to think outside the box, or explore outside the traditional boundaries of the disciplines.

3. It's important to build a comprehensive toolbox early. 

During my years as a student, I took many courses from many different departments. Some were due to degree requirements, while others were not closely related to the degrees I was pursuing. At that time, I often wondered whether those materials were going to be useful. For instance, as of today, I have never directly applied anything I learned w.r.t. assembly language. On the other hand, I have encountered a good number of problems that I could solve easily thanks to the tools I picked up in school. This paper is an example. The methodology we proposed involves clustering. To invent custom solutions to this novel problem, we need some decent understanding of optimization. Without those tools, I would have not even thought about customizing the hierarchy for hierarchical forecasting. 

4. IJF editors and reviewers are awesome!!!

This paper went through many rounds of review. I think it's four or five rounds. If counting the reproducibility check, it's even more. I really appreciate the detailed and constructive criticisms offered by the editors and reviewers. It took us a significant amount of time to revise the paper, which helped improve our work. Unfortunately I don't know who they are due to the double-blind review process. Here I want to express my sincere gratitude for them to invest the time helping us make the paper better.

My talk was very well attended with standing room only. Some folks later told me that they couldn't get into the session because the classroom was so packed. I think I made a good decision to break the status quo, by presenting a non-energy talk at ISF.

Mark your calendar for the 47th ISF, Paphos, Cyprus, June 20th to 23rd, 2027.

Lara Kretschmer: Captain

Today (April 14, 2025), Lara Kretschmer defended her master thesis Value-added Analysis of Electricity Price Forecasts via Battery-based Energy Arbitrage.

Lara received her bachelor's degree in mathematics and a graduate certificate in data science and business analytics from UNC Charlotte in May 2024. Right after that, she came to our department to pursue the master of science degree in engineering management. 

Lara Kretschmer's master thesis defense

From left to right: Dr. Tao Hong, Lara Kretschmer, Dr. Churlzu Lim. (on zoom: Dr. Lin Ma)

She set a record by finishing our MSEM program in just one year, with a thesis. 

She set this record while playing NCAA Division I volleyball!

Lara is a student athlete, born and raised in Germany. In 2020, she was recruited to UNC Charlotte on the athletics scholarship to play volleyball. In the 2024-25 season, also her 5th and last season at Charlotte, she served as a co-captain of our volleyball team. She was also named to the College Sports Communicators Academic All-District Team.

From her weekly reports, I can see many weeks of 70+ hours. Every week, she spent countless hours in the gym, for workouts, practices, and games.  Sometimes she had to travel to other states to play, adding another 10 to 20 hours on the road. On the academic side, I told all my BigDEAL students to take the most challenging courses on campus. Lara is of no exception. 

Lara is a straight-A student. 

I must be the luckiest professor in the world. I don't know what else I should dream of. 

Well, I wish she can continue pursuing her PhD, but Lara wanted to play volleyball. She plans to join a semi-pro volleyball team in Germany, while taking a day-time job in the industry.

Update 10/3/2025:

After graduation, Lara went back to Germany. She is a forecaster and demand planner at Delta Dore Rademacher, while she continues playing her favorite sports, volleyball, at a local semi-pro team. 

Lara visited me today with a hard-copy of her thesis. 

International Symposium on Energy Analytics 2025

I know some of you have been waiting for more than 7 years.... 

The 2nd International Symposium on Energy Analytics is only one month away. If you are not sure whether to attend ISEA2025 or not, here are seven reasons:

1. Join the IIF Distinguished Lecture Series, in person.

Electricity is the most volatile commodity in the world. Forecasting its prices is hard! Rafal Weron is going to deliver his IIF Distinguished Lecture Series on electricity price forecasting at ISEA2025. ISEA audience will be able to sit in the classroom taught by the electricity price forecasting guru.

2. Learn from the success stories of IIF-SAS awardees.

IIF and SAS has been in collaboration to offer the IIF-SAS award for more than 20 years. During the past decade, an energy forecasting proposal is awarded every one or two years. ISEA2025 includes presentations of five recent IIF-SAS awards in energy forecasting. ISEA audience will have the opportunity to learn from these funded projects, and hopefully become the next $10,000 award winner in the coming years.

3. Understand the emerging needs of the industry.

Renowned vendors and seasoned practitioners are speaking at ISEA2025, about the emerging problems and trending solutions. Whether you are a researcher looking for real-world problems, or a practitioner seeking benchmarks, ISEA is the place to be. 

4. Hire rising stars.

ISEA2025 has a special registration rate for students. There will be a student presentation session as well. Having a hard time to fill in the energy data scientist vacancies in your group? Come to ISEA to hire the rising stars. 

5. Connect with SWEET.

IIF Section on Water, Energy and Environment (SWEET) is the home for energy forecasters. The leadership team of SWEET will be attending ISEA2025. Let's talk to them and find out all the SWEET opportunities.

6. Network with Foresight practitioners.

ISEA2025 will be hosted in parallel with the Foresight Practitioners Conference, which features practitioner speakers and finalists of the inaugural Forecasting Practice Competition. Energy forecasters will have the opportunities to network with the forecasters from other business sectors. BTW, one of the finalists is an energy company!

7. Enjoy the IIF Foresight online membership for free. 

Thanks to the financial support from IIF and the Industrial and Systems Engineering Department of UNC Charlotte, we are able to keep the registration fees quite low. To put a cherry on top, we offer each paid registration one-year IIF Foresight online membership for free. 

ISEA2025 will be hosted at University of North Carolina at Charlotte, March 3-4, 2025, with the theme Energy Analytics: State of the Practice. Registration deadline is Feb 20th.

Look forward to seeing you in a month!

Congratulations, Dr. Shukla!

Today (November 3rd, 2023), Shreyashi Shukla defended her doctoral dissertation on short-term peak timing forecasting.

Shreyashi joined our MSEM program in Fall 2017. She completed her master thesis under my supervision in October 2018. After that, she continued working with me to pursue her PhD.

Since the first summer into her PhD program, Shreyashi started working half time at Duke Energy. She took a major role in helping millions of Duke Energy customers understand their electricity end uses. Her managers and colleagues all spoke highly of her work.

COVID hit us right in the middle of her PhD journey. She had to juggle several balls at the same time, the Duke Energy job, her dissertation research, and most importantly, her family. While many others were taking a break during the lockdown, she is making progress on her research.

Last year Shreyashi and I organized the BigDEAL Challenge 2022, which attracted 78 teams from 27 countries. She was heavily involved in the competition design. She also took most responsibilities of competition operations.

Her dissertation work is ahead of its time. The committee was very much impressed by the thoroughness and depth of the work. Within the next few years, her name will appear in some of the most influential papers in the load forecasting literature.

Congratulations, Dr. Shukla!

BigDEAL Challenge 2022 Final Leaderboard

BigDEAL Challenge 2022 attracted 78 teams formed by 121 contestants from 27 countries. 14 teams were advanced to the final match, an ex ante daily peak load forecasting competition. 

The final match includes 6 rounds of ex ante daily peak load forecast tasks. The data were released on a rolling basis. The forecasts were evaluated from three different perspectives: magnitude, timing, and shape, which made the three tracks of the final match. The contestants were asked to submit forecasts for all three tracks in each round. 

The following methodology was used to determine the winners:

• The teams are ranked for each individual round for each track. 
• The rank of a missing submission is imputed by the team's worst rank of the corresponding track. 
• A team has to complete at least 5 rounds to be eligible for the final leaderboard. 
• The grand champion is determined based on rankings of the highest ranked 5 rounds.

13 teams were eligible for the final leaderboard*:

* Gray entries are students from Dr. Hong's Energy Analytics class offered at UNC Charlotte. 

A few highlights:

• Amperon is the only team that ranks top 2 in all three tracks (No. 1 in magnitude; No. 2 in timing and shape).
• Team KIT-IAI is the only team that won two tracks (timing and shape). 
• 4 teams (Amperon, KIT-IAI, Overfitters, and swissknife) outperform Shreyashi's Recency Benchmark in all three rounds.
• Rajnish Deo is the best performing individual.
• Belinda Trotta is the highest ranked individual. 

Details of each track are listed below:

We are working with the teams and journals to have their winning methodologies published. For those of you who are interested in what they did in the competition, stay tuned...

Congratulations to all participating teams and UNC Charlotte students!

Tao Hong and Shreyashi Shukla

BigDEAL Challenge 2022 Qualifying Match Results

The qualifying match of BigDEAL Challenge 2022 is ex post one-year ahead load forecasting. 121 contestants from 27 countries formed 78 teams to join the challenge. 

The following data were provided to the contestants:

• hourly load data of a U.S. utility from 2002 to 2006, and 
• hourly temperatures of four virtual weather stations from 2002 to 2007. 

The qualifying match includes three tracks: 

• H (Hourly loads of one year). Contestants were asked to forecast the 8760 hourly loads of 2007. MAPE of the 8760 hourly loads was used to evaluate the forecasts. 
• M (Magnitude of 365 daily peaks). Contestants were asked to forecast the 365 daily peak loads of 2007. MAPE of the 365 daily peaks was used to evaluate the forecasts. 
• T (Timing of 365 daily peaks). Contestants were asked to forecast the timings of the 365 daily peak loads of 2007, represented by integers from 1 to 24. MAE of the 365 daily peak timings was used to evaluate the forecasts. 

43, 41, and 40  teams completed the track H, M, and T, respectively. Leaderboards of the three tracks are shown below. 

Teams beating Shreyashi's Recency Benchmark in any track are qualified for the final match. Congratulations to the following 14 teams (in alphabetical order)!

• Amperon
• BelindaTrotta
• EnergyHACker
• freshlobster
• KIT-IAI
• Overfitters
• peaky-finders
• RandomForecast
• SheenJavan
• swissknife
• Team SGEM KIT
• VinayakSharma
• X-Mines
• Yike Li

Stay tuned...

Tao Hong and Shreyashi Shukla

Congratulations, Dr. Li!

Today (Oct 6, 2022) Yike Li defended his doctoral dissertation on short-term ex ante load forecasting. 

Yike joined our MSEM program in Fall 2018. He completed his master thesis under my supervision in Spring 2020. After that, he continued working with me to pursue his PhD.

The COVID-19 pandemic did not slow him down at all. Instead, the lockdown days may have speeded up his research. Towards the end of his PhD journey, I was frequently surprised by the amount of work he has done within a short timeframe between our meetings. 

From January 2021 to May 2022, Yike worked at Duke Energy as a Data Scientist intern, where he built predictive models to understand consumer electricity usage. After that, he spent a summer with Cruise. While Yike received many offers during the past few months, he decided to bring his talent back to Cruise after graduation. 

While the load forecasting literature is dominated by ex post forecasting studies, many practical issues with ex ante forecasting have never been thoroughly studied. Yike's dissertation tackled some of the most difficult problems in ex ante load forecasting. I'm glad to see that he is applying these skills in the transportation sector. 

Thanks to Yike, I can tell my department chair: "My student makes more than your Dean!"

Congratulations, Dr. Yike Li!

BigDEAL Challenge 2022

Dear colleagues,

This is the registration form for BigDEAL Challenge 2022. Please feel free to forward the link (https://tinyurl.com/yc835zp5) to anyone you think might be interested.

The theme of BigDEAL Challenge 2022 is peak load forecasting. The competition includes a qualifying match and a final match. 

Each team will include up to four team members. All team members should fill in the form.

The qualifying match is ex post one-year ahead forecasting. The match includes three tracks: 1) H (hourly loads of one year); 2) M (magnitude of 365 daily peaks); and 3) T (timing of 365 daily peaks). Winners of the qualifying match will be invited to the final match. Additional details and instructions will be released together with the qualifying match data on Oct 31, 2022. 

The final match is ex ante day ahead peak load forecasting. The data will be released on rolling basis. Forecasts from the finalists will be judged based on magnitude and timing of daily peaks. Additional details and instructions will be released together with the final match data on Nov 15, 2022. 

Every team qualifying the final match will be invited to submit a paper to IET Smart Grid describing the methodology used in the competition. Selected winning team(s) will receive waiver of Article Processing Charges.

Important Dates

• Registration Open: Oct 4, 2022
• Registration Close: Oct 29, 2022
• Qualifying Match Data Release: Oct 31, 2022
• Qualifying Match Submission Due: Nov 10, 2022
• Qualifying Match Results Announcement: Nov 14, 2022
• Final Match 1st Data Release: Nov 15, 2022
• Final Match Submission Due: Dec 7, 2022
• Final Match Results Announcement: Dec 12, 2022

Tao Hong, PhD

Duke Energy Distinguished Professor and NCEMC Faculty Fellow of Energy Analytics

Director of Big Data Energy Analytics Laboratory (BigDEAL)

Department of Systems Engineering and Engineering Management

University of North Carolina at Charlotte

hong "AT" uncc.edu 

Jordan McCorey - MVP

Last Thursday (April 15th, 2021), Jordan McCorey defended his master thesis Forecasting Most Valuable Players of the National Basketball Association.

Jordan McCorey received his B.S. in Mechanical Engineering from NC A&T University in 2017. Right after graduation, he started his full time job at Boeing in North Charleston as a process engineer. He joined our Master of Science in Engineering Management as a part-time student in Fall 2018. 

Jordan McCorey's master thesis defense
From left to right: Dr. Tao Hong, Dr. Linquan Bai, Jordan McCorey, and Dr. Pu Wang

MVP, a.k.a. Most Valuable Player, is the highest individual award for the most performing player in the entire league. If I were asked to name the MVP among all the graduate students in our program during this pandemic year, Jordan McCorey would be the one.

I have always been interested in sports, basketball in particular. After ISF2019, I sent an email to our graduate students list with a few project topics. One topic was sports analytics - NBA forecasting. Jordan responded to my email with a passionate cover letter expressing his strong interest.

We quickly set up a phone call to discuss a plan to move forward. During the phone call, I was very pleasant to know that Jordan was a varsity basketball player in high school. His understanding of the game was definitely a big plus for this topic. On the other hand, I also got to know that he has limited experience in programming, statistics, and forecasting.

I explained the challenge to him. Apparently he didn't back off. Then I asked him to take my forecasting course, which is known as one of the most demanding courses on campus. The COVID-19 pandemic hit us right in the middle of Spring 2020 semester. Many students took the easy route by taking a passing grade. Jordan, however, worked extra hard to earn a solid A while working on his full-time job at Boeing. 

Due to the quarantine, I was never able to meet Jordan in person. Instead, we had many phone calls to discuss his plan of study, research progress, and of course, our shared passion about the game of basketball. 

A few weeks before his defense date, I got a call from Jordan telling me that he just had Achilles injury. That's the same injury that led to Kobe's retirement, and the same injury that took down Kevin Durant during Game 5 of 2019 final. I asked him if he wanted to postpone the defense. He said no.

Then it came the defense date. 

A fabulous presentation Jordan delivered. 

I was super impressed, so were the other two committee members. 

Jordan McCorey, MVP of the 2020-2021 academic year. 

Announcing Global Energy Forecasting Competition 2021: Solar and Net Load Forecasting

Dear colleagues and readers of this blog,

Last year at ISF2019 in Thessaloniki, Greece, I mentioned the possibilities of running the next Global Energy Forecasting Competition in the SWEET membership meeting. Then the COVID-19 pandemic put everything on hold. 

Today, I'm pleased to announce GEFCom2021: Solar and Net Load Forecasting. 

GEFCom2021 will feature two tracks, solar irradiance forecasting and net load forecasting. Dr. Dazhi Yang will chair the solar irradiance forecasting track, while I'm taking care of the net load forecasting track.

This competition will inherit the bi-level setup of GEFCom2017. We will use a qualifying match math to bring together contestants from various domains, and to help people get familiar with solar and load forecasting problems. Then a final match will determine the winners. 

Additional details of GEFCom2021 will be released in Spring 2021. Please join the email list via this REGISTRATION FORM to get timely updates about GEFCom2021.

Hope you all stay safe and enjoy the holiday season!

Tao