Prof. Feindt’s main experience and most successful research work is data driven software development, understanding and learning effects through data analysis, usage, further development and discovery of new multivariate statistical algorithms and respective software (today labelled “predictive analytics” or “machine learning’’) in big data environments. Real big data in modern particle collider experiments consist of PetaBytes of data per second and have to be reduced by a factor of about 1 million by automatic trigger systems before even stored to disk. Reconstruction and Monte Carlo simulations also run on the world wide Grid, predecessor of today’s commercial Cloud Computing.
Important work lies in the abstraction from the particular problem for an easy and successful transfer of these methods to other disciplines, and big data challenges in retail, various industries and financial services as well as real-time targeting mechanisms i.e. in online ad business.
In 2000 Prof. Feindt invented the NeuroBayes®-algorithm to predict future events by learning from samples of past events and developed it for usage in research and very different industries and applications like insurance, trading, retail, wholesale, finance, medicine, industry, customer relations. Key features of NeuroBayes® are its general approach for retail, industry and financial service problems, its robustness, speed, scalability and flexibility.
It cannot only predict the probability of binary events (final answer is yes or no, prediction output is probability of ”yes”), but also the complete probability density distribution of real-valued variables like turnover or price, which allows e.g. an optimal decision under uncertainty – a situation very common in almost any company.
At Blue Yonder he invented a number of further algorithms important for applications in retail and industry, now integral part of Blue Yonder’s proprietary machine learning library. These are e.g. the cyclic boosting algorithm for “explainable” predictions (vs. black box), an algorithm for isolating causal effects in historic data, and OR-by-AI using a combination of ideas from reinforcement learning, deep learning and NeuroBayes. Another highlight is the implementation of the NeuroBayes expert algorithm in FPGA hardware, in collaboration with KIT, for the Belle II experiment. Such a chip can calculate 8 billion intelligent decisions per second for deciding which parts of a sensor should be read out.
From 2005 to 2010 Prof. Feindt led his students to regularly participate in the Data Mining Cup (the world’s largest competition on intelligent data analysis and prediction, with about 650 participants from 140 Universities in 40 countries). Its results have always been top scores, number 1 in 2006 (predicting prices of ebay auctions), 2009 (predicting book sales in 8000 shops) and 2010 (predicting customer behaviour with the help of coupons) by applying NeuroBayes®.
More than 200 scientific publications and Ph.D. theses applied NeuroBayes® successfully, mainly large scale international particle physics experiments where Prof. Feindt is directly involved. However, NeuroBayes® is also applied in scientific projects without the participation of Prof. Feindt, e.g. in the trigger system of the LHCb-experiment at CERN where it plays a crucial role in the reduction of the huge data rates by distinguishing interesting from uninteresting events online before they can be stored permanently, the ATLAS experiment at CERN and in the planning of the AMS experiment on board of the international space station ISS.
Prof. Feindt founded the company Phi-T in 2002 and Blue Yonder in 2008 to professionalize and further develop NeuroBayes® and attracted substantial seed investment capital. Phi-T GmbH was also managing a market neutral 100 M€ low-risk absolute-return investment fund completely automatically on the basis of NeuroBayes®-predictions until it was stopped due to legal changes. Prof. Feindt currently is on leave of absence from the Karlsruhe Institute of Technology KIT, continuing the research work but having no teaching obligations and works 100% as Chief Science Officer for Blue Yonder.
Prof. Feindt is (co-) author of approx. 1280 scientific publications in renowned scientific journals. Many of these were with the PLUTO-, CELLO-, DELPHI-, CDF II-, Belle and CMS-Collaborations, large particle accelerator experiments at international research centers DESY(Hamburg), CERN (Geneva), Fermilab (Chicago) and KEK(Japan).
He gave more than 400 public talks, seminars and keynotes. His scientific work was recognized by e.g. the CERN Exceptional Performance Award (1995), the Landeslehrpreis Baden-Württemberg (2000), a large number of “best lectures“ prizes, as well as a large number of innovation prizes for Blue Yonder, e.g. bwcon 2012 (most innovative software company in Baden-Württemberg), Focus Digital Star 2013 (most innovative B2B software from Germany), finalist as Entrepreneur of the Year 2013, Deutscher Innovationspreis 2014 (with OTTO), IOTA Internet of Things Award 2014, Technology Review’s list of 50 world’s most innovative companies 2015, DataIQ100 most influential Big Data 2016 list, Big Data Leader Germany 2016, IFD Award for Supply Chain Innovation 2017 (with Morrisons), TOP 100 Innovator 2017, etc.
With the acquisition of Blue Yonder by JDA Software in 2018, Prof. Feindt moved to the role of Strategic Chief Scientist at JDA, not only responsible for evolving the Blue Yonder product portfolio but overseeing the scientific work at JDA on a global scale. He thus makes sure the combined technology of JDA and Blue Yonder is available to customers worldwide.
Prof. Feindt is reviewer and advisor to many physics journals, national funding agencies and the Helmholtz Gemeinschaft (heading all Germany’s national large scale research centers). He also advises the German federal and state governments on Artificial Intelligence.
He is co-founder and advisor to the Data Science Academy, and book author.
Research career at a glance
Since 1997 Prof. Dr. Feindt is professor of physics at the University of Karlsruhe (Germany), now called Karlsruhe Institute of Technology (KIT). He supervised more than 60 PhD theses and 70 diploma/master theses, and co-supervised another 100 theses. He leads a research group of about 20 scientists at KIT. Currently he is on leave of absence from KIT for working full time for Blue Yonder.
Prof. Feindt leads very successful research groups
at the until recently highest-energy proton-antiproton collider CDF-II- experiment at Fermilab (USA),
world’s highest luminosity low-energy-high-precision experiment Belle and its successor Belle II at the Japanese Laboratory KEK and
the CMS-experiment at the LHC collider at CERN.
Among the most respected results are the discovery of the time-dependent oscillations of BS-mesons into their antiparticles and back (CDF II 2006), and the spin-parity and mass measurements of the X(3872)-particle, giving evidence that this does not seem to be a normal meson but possibly a molecule of two mesons (CDF 2006, 2008).
A recent highlight was
the invention, implementation and application of a “full reconstruction factory” for the Belle-experiment, a software that performed roughly the equivalent of about 1100 Ph.D. theses fully automatically using about 70 NeuroBayes® networks and
managed to more than double the physics output for analyses which need fully reconstructed B-mesons, for one of the most successful particle accelerator experiments worldwide that already took data for 10 years operated by a collaboration of about 400 physicists from all over the world (Belle 2011), equivalent to an additional running cost of € 700 million.
A new version just released in 2017 for the successor experiment Belle II, written by PhD students of him, leads to another doubling of efficiency with respect to human work, together corresponding to a € 2.1 billion gain in running cost.
He also is author of financial mathematics papers and co-supervised PhD theses on econometrics.
Prof. Feindt introduced advanced data analysis courses for physics students and was
student’s dean of the faculty of physics from 1998 to 2003,
speaker of Germany’s largest graduate college (DFG-Graduiertenkolleg Hochenergiephysik und Teilchenastrophysik) with on average 70 Ph.D. students from 2003 to 2010 and
executive board member of the excellence cluster KCETA and excellence graduate school KSETA.
From 1991 to 1997 Dr. Feindt was working as scientific fellow and later as scientific staff member at the world’s largest particle accelerator laboratory, the European Center for Particle Physics CERN (Geneva, Switzerland), he made important (software and analysis) contributions to the DELPHI experiment at the world’s largest electron positron collider LEP and discovered e.g. first experimental evidence of so-called B** mesons.
From 1986 to 1991 he held a research position at the CELLO experiment at DESY.
In 1988 he received his Ph.D. in physics (“with distinction“) at the University of Hamburg on data analysis at DESY experiments (Hamburg).
Diploma thesis on the PLUTO experiment at the particle accelerator laboratory Deutsches Elektronen-Synchrotron DESY (Hamburg)
From 1978 to 1984 he studied physics at the University of Hamburg