After much exploratory and conceptual work, we are now entering a more hands-on phase in the project. This entails designing and implementing a platform prototype. For that purpose, Björn Krahl will temporarily strengthen our project team. Together we’ll develop an architecture and implement it.
On Friday, November 19, we will be presenting the current state of our project at the BUA Sharing Resources Monitoring meeting with poster session.
Daniel Conde has joined our group as a doctoral researcher. He was involved in the project since April 2021, finishing his Master thesis on the topic: „Data Science und Corona: Änderung des Mobilitätsverhaltens in Berlin“.
Now, we are looking forward to continuing our work together and are sending you a warm welcome!
On August 14th, our undergraduate research seminar on Information Systems ended. Students had been working on projects from different areas within the Information Systems science, some of which focussing on topics directly related to the mobility data hub.
The research project tasks involved mapping the platform ecosystem, designing of a possible architecture, and preparing and analyzing first relevant data sets (i.e. GPS-based mode choices and the public transport timetable information).
The seminar was conducted by Prof. Natalia Kliewer and David Rößler at Freie Universität Berlin.
In late June, Nicki Kämpf and Jonas Krembsler presented first results from the research project “ReComMeND“ of fare revenue forecasting in public transportation in Berlin as part of our doctoral colloquium. The research project is funded by the IFAF Berlin and supported by Berliner Verkehrsbetriebe AöR, Internationaler Controller Verein e.V., Lufthansa Systems GmbH & Co. KG and Lufthansa Industry Solutions GmbH.
For their research, they use data based on monthly fare revenues for different product segments. The results will be used in a research project in public transport with the goal of automating revenue controlling and implementing data-driven decision-making in the existing controlling processes.
The focus of their study is to obtain suitable and reliable predictions: on the one hand with autoregressive methods such as ARIMA, SARIMA as well as Holt-Winters Exponential Smoothing and on the other hand with methods that include exogenous variables such as SARIMAX, MLR, LASSO, Ridge, Random Forests, Gradient Boosting, and Neural Networks. The data concerning exogenous variables are freely available and cover a wide range from tourism data to labor market development and weather data.
In their work, the researchers discuss the different methods and compare the prediction results by means of common accuracy measures. The goal is to evaluate a wide range of different methods in order to decide in which situations they out- or underperform other methods.
Besides simple prediction accuracy, another part of the study is the feature selection and interpretation of their impact. They address automatic feature selection using traditional approaches such as AIC optimization, a rolling window cross-validation approach optimizing the cv-error, and algorithmic approaches such as LASSO or Bayesian optimization. The researchers discuss the interpretability of the results and the advantages and disadvantages of different approaches.
The Berlin Mobility Data Hub has established a close cooperation with another project funded by the Berlin University Alliance (BUA), the „Berlin Open Science Platform“ (BOS), coordinated by the Quality and Usability Lab of TU Berlin. In similarity to our project, BOS aims to establish a data platform that gathers and integrates available data within the BUA. Beyond that, the platform aims to provide analytical features within the platform. Despite our project having a more specific thematic focus (mobility & transport), we regularly meet with the BOS project team in order to exchange ideas on the technical side of developing our platforms.