KDD Cup 2018

Air pollution is affecting our life every day. For many large cities, it had become a severe problem that worsened progressively in the past few years. This year’s KDD Cup, titled KDD Cup of Fresh Air, solicits machine learning solutions to accurately forecast air quality indices (AQIs) of the future 48 hours. Accurate predictions of AQIs can bring enormous value to governments, enterprises, and the general public - and help them make informed decisions.

KDD Cup of Fresh Air was launched on March 15th and ended on May 31st. Participants are asked to forecast the AQIs of Beijing, China and London, UK. Over 4,000 teams from 49 countries participated in the competition, and made over 20,000 submissions.

The total prize of $36,500 was awarded to top 10 teams in the regular track and top 3 teams in each of two special tracks. Top teams are invited to present their solutions at the KDD Cup Workshop held on August 21st in London, during the KDD 2018 conference.

More details on the competition can be found at https://biendata.com/competition/kdd_2018. It was a great opportunity for participants to contribute their expertise in data science, machine learning, and artificial intelligence to the social good, win valuable prizes, and travel to beautiful London.

KDD CUP WORKSHOP PROGRAM

KDD Cup 2018 Workshop will be held on August, 21st 2018 during the KDD conference at Excel London.

During the workshop, top teams will share their winning solutions that defeated over four thousand teams across the world.

We are also thrilled to have six leading experts from the industry, government and competition community for two keynotes and a panel discussion.

Please join us at KDD Cup 2018 workshop.

KEYNOTE SPEAKERS

Rosalind O’Driscoll, Ph.D.

Dr Rosalind O’Driscoll is a Senior Policy Officer for Air Quality at the Greater London Authority (GLA). Her role involves modelling for the London Environment Strategy and London Atmospheric Emissions Inventory. Before joining the GLA Rosalind graduated from Imperial College London with a PhD addressing uncertainties in real world emissions from passenger cars, and modelling the policy implications of these uncertainties.

Marios Michailidis, Ph.D.

Marios Michailidis is one of the most well-known competitive data scientists who was ranked #1 out of half a million competitors on Kaggle. Marios is currently a competitive data scientist at H2O.ai, where he works on Driverless AI, a machine learning automation software. Prior to H2O.ai, he was a data science manager at Dunnhumby. He is also a creator of StackNet, an open source ensemble-learning framework. He holds a BSc in Accounting Finance from the University of Macedonia in Greece, an MSc in Risk Management from the University of Southampton, and a PhD in Machine Learning from the University College London (UCL).

PANELISTS

Claudia Perlich, Ph.D.

Claudia Perlich is a Senior Data Scientist at Two Sigma in New York City. Prior to her role at Two Sigma, she was the Chief Scientist at Dstillery where she designed, developed, analyzed, and optimized machine learning that drives digital advertising to prospective customers of brands. She started her career in Data Science at the IBM T.J. Watson Research Center, concentrating on research in data analytics and machine learning for complex real-world domains and applications. She tends to be domain agnostic having worked on almost anything from Twitter, DNA, server logs, CRM data, web usage, breast cancer, movie ratings and many more. Perlich is an active public speaker and has published over 50 scientific publications as well as a few patents in the area of machine learning. She received her PhD in Information Systems from the NYU Stern School of Business, and holds a Master of Computer Science from Colorado University.

Jacob Spoelstra, Ph.D.

Jacob is the Director of Data Science at Microsoft where he leads a group of machine learning specialists focused on helping Microsoft’s enterprise customers develop and deploy advanced analytics solutions. Previously he led the Azure Data Group where his team was responsible for machine learning-based products and processes on the Microsoft AI stack. Prior to Microsoft, Jacob was the global head of R&D at Opera Solutions, where he led the development of key Opera innovations, including a patented adaptive auto auction pricing solution utilizing Kalman filters, and collaborative filtering techniques to detect revenue leakages in medical bills. He headed up the Opera Solutions team that, as part of “The Ensemble,” ended up “first equals” in the Netflix Grand Prize, beating out over 41,000 other entrants. Jacob has held analytics leadership positions at FICO, SAS, ID Analytics, and boutique consulting company BasePoint. He holds BS and MS degrees in Electrical Engineering from the University of Pretoria, and a PhD in Computer Science from the University of Southern California.

Marios Michailidis, Ph.D.

Marios Michailidis is one of the most well-known competitive data scientists who was ranked #1 out of half a million competitors on Kaggle. Marios is currently a competitive data scientist at H2O.ai, where he works on Driverless AI, a machine learning automation software. Prior to H2O.ai, he was a data science manager at Dunnhumby. He is also a creator of StackNet, an open source ensemble-learning framework. He holds a BSc in Accounting Finance from the University of Macedonia in Greece, an MSc in Risk Management from the University of Southampton, and a PhD in Machine Learning from the University College London (UCL).

Abhishek Thakur, M.S.

Abhishek is a data science evangelist. He currently works as chief data scientist at boost.ai building state-of-the-art chatbots primarily for banking and insurance industries. His passion lies in solving difficult world problems through data science. He is the co-organizer of the Berlin Machine Learning Meetup and not long ago was ranked no. 3 worldwide on the Data Science Platform Kaggle. Abhishek did his Bachelors in Electronics Engineering from India and moved to Germany for pursuing MSc from University of Bonn, Germany with a focus on image processing and computer vision. He dropped out of PhD in 2015 and since then has been working in industries.

Gilberto Titericz, M.S.

Gilberto is a Lead Data Scientist at Ople.ai, where he develops AI products that automate data science process. Prior to Ople.ai, he worked at AirBnB, Petrobras, and Siemens. Gilberto is well-known for his track record in machine learning competitions. He participated in over one hundred competitions, won at fourteen competitions, and finished top 10 at over thirty competitions. He held #1 rank at Kaggle for more than two years. He holds a BSc in Electrical Engineering and a MSc in Telecommunications from the UTFPR in Curitiba, Brazil.

KDD CUP 2018 WINNERS

Regular Track

First prize ($10,000): First floor to eat Latiao (Haoran Jiang and Binli Luo from Central South University, Jindong Han, Juan Liu, and Qianqian Zhang from Beijing University of Posts and Telecommunications)

Second prize ($5,000): getmax (Zhipeng Luo from Microsoft, Jianqiang Huang from Peking University, and Ke Hu from Alibaba)

Third Prize ($3,000): 头号玩家@ICA@CortexLabs (Jie Zhou from East China Normal University, Hengxing Cai from Sun Yat-Sen University and Cortex Labs, and Xiaozhou Liu from Sun Yat-Sen University)

Honorable Prizes ($500 each)

4th place: deepx

5th place: 迟到大队 (The Late Team)

6th place: oneday

7th place: ToBeDone

8th place: 613啪啪队 (613PaPaTeam)

9th place: Tony2018

10th place: To be determined.

Special Prize for the Last 10-Day Prediction

First prize ($5,000): getmax

Second Prize ($3,000): deepx

Third Prize ($2,000): First floor to eat Latiao

Special Prize for the Second 24-Hour Prediction 

First prize ($2,500): getmax

Second Prize ($1,500): 头号玩家@ICA@CortexLabs (Ready Player One@ICA@CortexLabs)

Third Prize ($1,000): 迟到大队 (The Late Team）

Sponsors