Oliver Gindele

Company: Datatonic

Job Title: Data Scientist

Oliver Gindele

Oliver is a Data Scientist at Datatonic with a background in computational physics and high performance computing. He is a machine learning practitioner who recently started exploring the world of deep learning. Datatonic partners with Google Cloud Platform to build state of the art machine learning and data analytics solutions, providing customers with actionable business insight.

Twitter LinkedIn

Oliver Gindele Seminars

  • Predicting congestion on London’s roads with Beam and Tensorflow Wed 4th Oct 12:20 - 12:50

    Predicting congestion on London’s roads with Beam and Tensorflow

    Predicting congestion is an important part of any traffic management system. With accurate forecasting traffic can be effectively regulated, ensuring safe and fast journeys on the roads. In this work we present a deep learning model which accurately forecasts congestion based on road sensor data from Transport for London (TfL).

    The IoT (internet of things) nature and scale of the raw sensor data demands extensive preprocessing as a first step towards a predictive traffic model. We used Apache Beam for this task as it let us create efficient data pipelines which can be executed in distributed frameworks such as Apache Spark of Apache Flink. Beam natively handles streaming workloads which makes it an ideal candidate for large scale preprocessing of real-time data such as streams from road sensors.

    The preprocessed data was then used to train a neural network to predict the congestion ahead of time. A recurrent neural network (RNN) was chosen to model the traffic time-series for each of the sensors. This deep learning architecture was implemented in Tensorflow and it allowed us to accurately model the time-series and the correlations between the sensors on the road network. With this end-to-end example we demonstrate how Beam and Tensorflow can be used to build predictive models for time series data.


    Oliver Gindele

    Oliver GindeleMore

    Time / Place

    Wed 4th Oct 12:20 to 12:50

    Data Analytics