Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Master’s thesis: Classifying patents with ML for clean energy innovation policy
The Energy Politics Group (EPG) offers a master’s thesis that aims to analyze patents with methods from natural language processing and machine learning. We are looking for an excellent student with experience and interest in applied machine learning, text analysis, and energy policy.
Keywords: clean energy technologies; machine learning; natural language processing; patents; public policy; energy; climate change
At the Energy Politics Group (EPG) we support policy makers in designing “technology-smart” policies. While existing studies have often relied on experts to characterize technologies, there is the need to develop more quantitative approaches to support innovation policy in a consistent, replicable and scalable way. One such promising data-driven approach is based on text processing of patent data with machine learning to characterize clean energy technologies in terms of their determinants of innovation. EPG offers a master’s thesis that aims to analyze patents with methods from natural language processing and machine learning. We are looking for an excellent student with experience and interest in applied machine learning and text analysis. Fluency in English and experience with statistical analysis are required. Strong communication and project management skills, knowledge of Python or R, and an interest in technological innovation and energy policy are an asset. We are open in terms of disciplinary background and master's program. Applications from non-ETH students are also welcome.
The master’s student will work in close
collaboration with Dr. Lynn Kaack and Dr.
Abhishek Malhotra, two post-doctoral
researchers at EPG, as well as Prof. Tobias
Schmidt. The student will have the opportunity
to become an integral part of the EPG research
team and contribute to EPG’s research agenda.
The duration of the thesis is 6 months. Ideally,
the start would be fall of 2019.
At the Energy Politics Group (EPG) we support policy makers in designing “technology-smart” policies. While existing studies have often relied on experts to characterize technologies, there is the need to develop more quantitative approaches to support innovation policy in a consistent, replicable and scalable way. One such promising data-driven approach is based on text processing of patent data with machine learning to characterize clean energy technologies in terms of their determinants of innovation. EPG offers a master’s thesis that aims to analyze patents with methods from natural language processing and machine learning. We are looking for an excellent student with experience and interest in applied machine learning and text analysis. Fluency in English and experience with statistical analysis are required. Strong communication and project management skills, knowledge of Python or R, and an interest in technological innovation and energy policy are an asset. We are open in terms of disciplinary background and master's program. Applications from non-ETH students are also welcome. The master’s student will work in close collaboration with Dr. Lynn Kaack and Dr. Abhishek Malhotra, two post-doctoral researchers at EPG, as well as Prof. Tobias Schmidt. The student will have the opportunity to become an integral part of the EPG research team and contribute to EPG’s research agenda. The duration of the thesis is 6 months. Ideally, the start would be fall of 2019.
EPG offers a master’s thesis that aims to analyze
patents with methods from natural language
processing and machine learning. The student’s
task will comprise, amongst others:
• Reviewing the relevant literature.
• Developing a classifier to discriminate patent
data based on patent texts.
• Developing a clustering algorithm to identify
technology characteristics from patent texts.
EPG offers a master’s thesis that aims to analyze patents with methods from natural language processing and machine learning. The student’s task will comprise, amongst others: • Reviewing the relevant literature. • Developing a classifier to discriminate patent data based on patent texts. • Developing a clustering algorithm to identify technology characteristics from patent texts.
Your application documents should include a
short letter of motivation that includes a
description of the relevant experience (max. one
page), a CV, and transcript of records (with
grades). Please send your complete documents
by e-mail to:
Lynn Kaack (lynn.kaack@gess.ethz.ch).
At www.epg.ethz.ch you can find more
information about the group. The review of
applications will start immediately after
publication of this ad and will continue until the
position is filled.
Your application documents should include a short letter of motivation that includes a description of the relevant experience (max. one page), a CV, and transcript of records (with grades). Please send your complete documents by e-mail to: Lynn Kaack (lynn.kaack@gess.ethz.ch). At www.epg.ethz.ch you can find more information about the group. The review of applications will start immediately after publication of this ad and will continue until the position is filled.