Мы используем файлы cookie для быстрой и удобной работы сайта. Выберите, какие файлы cookie вы разрешаете нам использовать. Подробнее в Политике конфиденциальности.
We use cookies to ensure our website works quickly and easily. Choose which cookies you allow us to use. Learn more in our Privacy Policy.
Обсудить проект
Отправьте запрос, и наши специалисты свяжутся с вами в течение 1 часа
Нажимая кнопку «Отправить», Вы даете однозначное согласие на обработку своих персональных данных в объеме и с целями, определенными Политикой в отношении обработки персональных данных.
Discuss the project
Send a request and our specialists will contact you within 1 hour.
By clicking the "Send" button, you give your unambiguous consent to the processing of your personal data to the extent and for the purposes defined in the Personal Data Processing Policy.
Predicting the success of construction waste removal flights
at the time of flight launch
5%
95%
the number of successful flights has increased
by
by
the accuracy of flight success forecasting has increased
Customer
A large construction company in the Moscow region
CHALLENGES/FEATURES
The success of each flight depended on strict compliance with regulatory criteria: the presence of geocoordinates for the vehicle every 15 seconds of the flight, the vehicle being no further than 100 m from the testing area at the end of the flight, etc.
Predicting the success of waste removal flights at the time of their launch to proactively respond to incorrect flights
Task
Technical solution
1. Conducted a study, identified patterns and factors that influence the success of waste removal
2. Machine learning (ML) and data analysis methods were applied:
Using the open-source TabNet and LGBM libraries, we implemented two flight success prediction models. The models were trained on the customer's historical flight data and are capable of making accurate flight success predictions at the time of flight commencement.
We compared the models and selected the one with the highest accuracy
Business values
Effective waste management
proactive response to potentially incorrect flights
The working group's time spent analyzing incorrect flights after their completion has been reduced by 3 times
reducing costs and minimizing financial losses from incorrect waste removal trips
A 5% increase in successful flights due to proactive response from dispatchers after the model's implementation
Identification of key factors
Understanding which factors and conditions influence the success of flights - constants and variables: carrier, driver, departure time, landfill, type of waste being removed, weather conditions, permit specifications, etc.
Accuracy
predicting flight success with up to 95% accuracy
By clicking the "Submit" button, you expressly consent to the processing of your personal data to the extent and for the purposes defined in the Personal Data Processing Policy.
Development of software
and Big Data solutions
and Big Data solutions
Send a request and our specialists will contact you within 1 hour.
Choose a convenient method of communication
You can attach three files up to 3 MB each. Formats: doc, docx, pdf, ppt, pptx
Сообщение об успешной отправке!