Conserve Water Resources by Predicting Timeseries (ML Competition for €20,000)

This is one of the challenges in the DrivenData competition series run by Schneider Electric. Each challenge explores a different aspect of energy efficiency, water conservation, and smart management of natural resources in an era of environmental change. The winning algorithms from these competitions are released under an open source license in order to spread understanding of these data challenges and what approaches are most effective.

Sustainable Industry: Rinse Over Run

Efficient cleaning of production equipment is vital in the Food & Beverage industry. Strict industry cleaning standards apply to the presence of particles, bacteria, allergens, and other potentially dangerous materials. At the same time, the execution of cleaning processes requires substantial resources in the form of time and cleaning supplies (e.g. water, caustic soda, acid, etc.).

Given these concerns, the cleaning stations inspect the turbidity—product traces or suspended solids in the effluent—remaining during the final rinse. In this way, turbidity serves as an important indicator of the efficiency of a cleaning process. Depending on the expected level of turbidity, the cleaning station operator can either extend the final rinse (to eliminate remaining turbidity) or shorten it (saving time and water consumption).

The goal of this competition is to predict turbidity in the last rinsing phase in order to help minimize the use of water, energy and time, while ensuring high cleaning standards.

This competition will include two stages:

• Stage 1: Prediction Competition (Jan 11 - March 1) is the open machine learning competition, where participants will submit predictions for the quantity of turbidity returned during the final rinsing process.
• In Stage 2: Modeling Report Competition (March 1 - March 18), the top 15 finalists from Stage 1 will have the opportunity to submit brief reports that analyze quantitative patterns in the data and help illuminate which signal(s) at which moment(s) is/are mainly responsible for the presence of turbidity during the final rinse. For more on each stage, see the Problem Description .

March 1, 2019, 11:59 p.m. UTC

Submissions to Stage 1 close.

Place Prize Amount 1st €500 2nd €500 3rd €500 4th €500 5th €500 6th €500 7th €500 8th €500 9th €500 10th €500 11th €500 12th €500 13th €500 14th €500 15th €500

Stage 1: Prediction Competition

Evaluated on predicted labels, final rankings displayed on the private leaderboard.

Prize Amount 1st €8,000 2nd €3,000 3rd €1,500

Stage 2: Modeling Report Competition

Evaluated on reports providing statistical reasoning about the models. The top 15 finalists from Stage 1 will have the opportunity to submit reports. Final winners will be selected by a judging panel.

Note: Prizes delivered by DrivenData in USD, based on the exchange rate on January 11, 2019.

Stay in touch!

Schneider Electric wants to stay in touch with competition participants in order to follow up about the algorithms, methods, and participation in this competition. To indicate you are open to being contacted by Schneider Electric, please add your name and email below!