CV: In 2002 Fabian Moerchen graduated from the University of Wisconsin, Milwaukee with the Master of Science. His thesis work on training neural networks in parallel on a cluster of computers was published in the IEEE Transactions of Neural Network. He joined the research group of Prof. Dr. Ultsch at the Philipps-University of Marburg, Germany and graduated with the PhD in 2006. The research on temporal pattern mining, music information retrieval, and self-organizing maps led to numerous conference and journal publications. At Siemens Corporate Research he worked from 2006 to 2012 as a research scientist and manager developing data driven decision support systems using machine learning and data mining. The applications included preventative maintenance, bio-informatics, medical imaging, financial risk scoring, and text mining. At Amazon, he started as manager in the Search & Discovery group using big data analytics to improve the vast product catalog of Amazon. He is currently a Principal Machine Learning Scientist for Amazon Music working on personalization, recommenders, bandits, offline policy evaluation, natural language understanding, entity resolution, and audio content understanding. 
Web:  
Publications:

2020

Moerchen, F., Ernst, P., Zappella, G.: Personalizing Natural Language Understanding using Multi-armed Bandits and Implicit Feedback, In Proceedings 29th ACM International Conference on Imformation and Knowledge Management, (2020) PDF

2019

Tatti, N., Moerchen, F., Calders, T.: Finding Robust Itemsets Under Subsampling, CoRR (2019), pp. 705-714 PDF

2016

Batal, I. and Cooper, G. and Fradkin, D. and Harrison, J. and Moerchen, F. and Hauskrecht, M.: An Efficient Pattern Mining Approach for Event Detection in Multivariate Temporal Data, Knowledge and Information Systems 46(1)(2016), pp. 115-150

2015

Fradkin, D., Moerchen, F.: Mining Sequential Patterns for Classification, Knowledge and Information Systems 45(3)(2015), pp. 731-749

2014

Sipos, R., Fradkin, D., Moerchen, F., Wang, Z.: Log-based Predictive Maintenance, In Proceedings 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2014), pp. 1867-1876 PDF
Sipos, R., Fradkin, D., Moerchen, F., Wang, Z.: Log-based Predictive Maintenance, In Proceedings 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2014), pp. 1867-1876 PDF
Lam, H.T., Moerchen, F., Fradkin, D., Calders, T.: Mining Compressing Sequential Patterns, Statistical Analysis and Data Mining 7(1)(2014), pp. 34-52 PDF
Tatti, N., Moerchen, F.: Finding Robust Itemsets Under Subsampling, ACM Transactions on Database Systems 39(3)(2014) TODS

2013

Lam, H.T., Calders, T., Yang, J., Moerchen, F., Fradkin, D.: Zips: Mining Compressing Sequential Patterns in Streams, In Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration and Analytics, (2013), pp. 54-62 IDEA
Lahiri, B., Moerchen, F., Akrotirianakis, I.: Finding Critical Thresholds for Defining Bursts in Event Logs, Transactions on Large-Scale Data- and Knowledge-Centered Systems (TLDKS) (2013) Technical Report

2012

Batal, I. and Fradkin, D. and Harrison, J. and Moerchen, F. and Hauskrecht, M.: Mining recent temporal patterns for event detection in multivariate time series data, In The 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2012), pp. 280-288 PDF
Wang, Q. and Zhang, K. and Marsic, I. and Li, J. K. J. and Moerchen, F.: Patient-friendly detection of early peripheral arterial diseases (PAD) by budgeted sensor selection, In PervasiveHealth, (2012), pp. 89-96 IEEE
Zhang, K., Lan, L., Liu, J., Rauber, A., Moerchen, F.: Inductive Kernel Low-rank Decomposition with Priors: A Generalized Nystrom Method, International Conference on Machine Learning (ICML) (2012) ICML
Zhang, K., Lan, L., Wang, Z., Moerchen, F.: Scaling up Kernel SVM on Limited Resources: A Low-rank Linearization Approach, Journal of Machine Learning Research - Proceedings Track 22(2012), pp. 1425-1434 JMLR
Lam, H.T., Moerchen, F., Fradkin, D., Calders, T.: Mining Compressing Sequential Patterns, In SIAM International Conference on Data Mining, (2012), pp. 319-330 PDF

2011

Lahiri, B., Moerchen, F., Akrotirianakis, I.: Finding Critical Thresholds for Defining Bursts, In Proceedings of the 13th International Conference on Data Warehousing and Knowledge Discovery (DaWaK), (2011), pp. 484-495 Technical Report
Tatti, N., Moerchen, F.: Finding Robust Itemsets Under Subsampling, In Proceedings IEEE International Conference on Data Mining, (2011), pp. 705-714
Moerchen, F.: Temporal pattern mining in symbolic time point and time interval data, In Tutorial, SIAM International Conference on Data Mining, (2011) SDM 2011
Moerchen, F., Thies, M., Ultsch, A.: Efficient mining of all margin-closed itemsets with applications in temporal knowledge discovery and classification by compression, Knowledge and Information Systems 29(1)(2011), pp. 55-80 Springer
Malik, H.H., Fradkin, D., Moerchen, F.: Single Pass Text Classification by Direct Feature Weighting, Knowledge and Information Systems 28(1)(2011), pp. 79-98 Springer

2010

Moerchen, F.: Temporal pattern mining in symbolic time point and time interval data, In Tutorial, Fifteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2010) KDD 2012
Fradkin, D., Moerchen, F.: Margin-Closed Frequent Sequential Pattern Mining, In Proceedings Useful Patterns Workshop, Fifteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2010)
Malik, H.H., Kender, J.R., Fradkin, D., Moerchen, F.: Hierarchical document clustering using local patterns, Data Mining and Knowledge Discovery 21(1)(2010) Springer
Moerchen, F., Fradkin, D.: Robust mining of time intervals with semi-interval partial order patterns, In Proceedings SIAM Conference on Data Mining, (2010), pp. 315-326

2009

Dejori, M., Malik, H.H., Moerchen, F., Neubauer, C.: Development of data infrastructure for the Long Term Bridge Performance program, In Proceedings of the Structures Congress (ASCE), (2009)
Yu, Y., Joe, K., Oria, V., Moerchen, F., Downie, J.S., Chen, L.: Multi-Version Music Search Using Acoustic Feature Union and Exact Soft Mapping, Int. J. Semantic Computing 3(2)(2009), pp. 209-234 PDF

2008

Moerchen, F.: Organic pie charts, In Proceedings IEEE International Conference on Data Mining, 30, (2008), pp. 947-952
Moerchen, F., Fradkin, D., Dejori, M., Wachmann, B.: Emerging trend prediction in biomedical literature, In Proceedings American Medical Informatics Association (AMIA) 2008 Annual Symposium, 29, (2008) PDF
Yu, Y., Downie, J.S., Moerchen, F., Chen, L., Joe, K.: Using Exact Locality Sensitive Mapping to Group and Detect Audio-Based Cover Songs, In Proceedings 10th IEEE International Symposium on Multimedia (ISM), IEEE Computer Society, (2008), pp. 302-309 IEEE
Yu, Y., Downie, J.S., Moerchen, F., Chen, L., Joe, K., Oria, V.: COSIN: content-based retrieval system for cover songs, Abdulmotaleb El-Saddik and Son Vuong and Carsten Griwodz and Alberto Del Bimbo and K. Selccuk Candan and Alejandro Jaimes (Eds), In Proceedings 16th ACM International Conference on Multimedia, ACM, (2008), pp. 987-988 ACM
Moerchen, F., Dejori, M., Fradkin, D., Etienne, J., Wachmann, B., Bundschus, M.: Anticipating annotations and emerging trends in biomedical literature, In Proceedings Thirteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 26, (2008), pp. 954-962
Renner, S., Derksen, S., Radestock, S., Moerchen, F.: Maximum Common Binding Modes (MCBM): Consensus Docking Scoring Using Multiple Ligand Information and Interaction Fingerprints, Journal of Chemical Information and Modeling ACS Publications, (2008) ACS

2007

Weihs, C., Ligges, U., Moerchen, F., Mllensiefen, D.: Classification in Music Research, Advances in Data Analysis and Classification 1(3)Springer, (2007), pp. 255-291 SpringerLink
Moerchen, F., Brinker, K., Neubauer, C.: Any-time clustering of high frequency news streams, In Proceedings Data Mining Case Studies Workshop (DMCS), The Thirteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,, San Jose, CA, USA, 23, (2007)
Risi, S., Moerchen, F., Ultsch, A., Lewark, P.: Visual mining in music collections with Emergent SOM, In Proceedings Workshop on Self-Organizing Maps (WSOM), Bielefeld, Germany, (2007)
Moerchen, F.: Unsupervised pattern mining from symbolic temporal data, SIGKDD Explorations 9(1)ACM, (2007), pp. 41-55 ACM
Moerchen, F., Ultsch, A.: Efficient Mining Of Understandable Patterns From Multivariate Interval Time Series, Data Mining and Knowledge Discovery 15(2)Springer, (2007), pp. 181-215 SpringerLink

2006

Moerchen, F., Mierswa, I., Ultsch, A.: Understandable Models Of Music Collections Based On Exhaustive Feature Generation With Temporal Statistics, Tina Eliassi-Rad, Lyle H. Ungar, Mark Craven, Dimitrios Gunopulos (Eds), In Proceedings The Twelveth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Philadelphia, PA, USA, (2006), pp. 882-891 ACM Digital Library
Moerchen, F.: A better tool than Allen's relations for expressing temporal knowledge in interval data, In Proceedings Temporal Data Mining Workshop (TDM), The Twelveth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Philadelphia, PA, USA, (2006)
Moerchen, F.: Algorithms For Time Series Knowledge Mining, Tina Eliassi-Rad, Lyle H. Ungar, Mark Craven, Dimitrios Gunopulos (Eds), In Proceedings The Twelveth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Philadelphia, PA, USA, (2006), pp. 668-673 ACM Digital Library
Moerchen, F.: Time Series Knowledge Mining, Phd Thesis, Philipps-University Marburg, Germany, Goerich & Weiershuser, Marburg, Germany, (2006), pp. 180 ISBN 3-89703-670-3
Noecker, M., Moerchen, F., Ultsch, A.: Fast and reliable ESOM learning, M. Verleysen (Eds), In Proceedings 14th European Symposium on Artificial Neural Networks (ESANN'06), Bruges, Belgium, (2006), pp. 131-136
Moerchen, F., Ultsch, A., Thies, M., Loehken, I.: Modelling timbre distance with temporal statistics from polyphonic music, IEEE Transactions on Speech and Audio Processing 14(1)IEEE Press, (2006), pp. 81-90 IEEE Xplore
Moerchen, F., Ultsch, A., Hoos, O.: Extracting interpretable muscle activation patterns with Time Series Knowledge Mining, International Journal of Knowledge-Based & Intelligent Engineering Systems 9(3)(2006), pp. 197-208

2005

Moerchen, F., Ultsch, A., Noecker, M., Stamm, C.: Databionic visualization of music collections according to perceptual distance, Joshua D. Reiss, Geraint A. Wiggins (Eds), In Proceedings 6th International Conference on Music Information Retrieval (ISMIR 2005), London, UK, (2005), pp. 396-403
Moerchen, F., Ultsch, A.: Optimizing Time Series Discretization for Knowledge Discovery, Grossman, R.L., Bayardo, R., Bennet, K., Vaidya, J. (Eds), In Proceedings The Eleventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, IL, USA, (2005), pp. 660-665 ACM Digital Library
Ultsch, A., Moerchen, F.: ESOM-Maps: tools for clustering, visualization, and classification with Emergent SOM, Technical Report No. 46, Dept. of Mathematics and Computer Science, University of Marburg, Germany, (2005)
Moerchen, F., Ultsch, A., Noecker, M., Stamm, C.: Visual mining in music collections, In Proceedings 29th Annual Conference of the German Classification Society (GfKl 2005), Springer, Heidelberg, (2005), pp. 724-731
Moerchen, F., Ultsch, A.: Finding persisting states for knowledge discovery in time series, In From Data and Information Analysis to Knowledge Engineering - Proceedings 29th Annual Conference of the German Classification Society (GfKl 2005), Magdeburg, Germany, Springer, Heidelberg, (2005), pp. 278-285 url SpringerLink
Moerchen, F., Ultsch, A., Thies, M., Loehken, I. and Noecker, M., Stamm, C., Efthymiou, N., Kmmerer, M.: MusicMiner: Visualizing timbre distances of music as topographical maps, Technical Report No. 47, Dept. of Mathematics and Computer Science, University of Marburg, Germany, (2005)
Moerchen, F., Ultsch, A.: Discovering Temporal Knowledge in Multivariate Time Series, Weihs, C., Gaul, W. (Eds), In Classification; The Ubiquitous Challenge, Proceedings 28th Annual Conference of the German Classification Society (GfKl 2004), Dortmund, Germany, Springer, Heidelberg, (2005), pp. 272-279

2004

Moerchen, F., Ultsch, A., Hoos, O.: Discovering interpretable muscle activation patterns with the Temporal Data Mining Method, Jean-Franccois Boulicaut, Floriana Esposito, Fosca Giannotti and Dino Pedreschi (Eds), In Knowledge Discovery in Databases: Proceedings 8th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2004), Pisa, Italy, Springer, (2004), pp. 512-514
Moerchen, F., Ultsch, A.: Mining Hierarchical Temporal Patterns in Multivariate Time Series, Susanne Biundo, Thom W. Frhwirth, Gnther Palm (Eds), In KI 2004: Advances in Artificial Intelligence, Proceedings 27th Annual German Conference in AI, Ulm, Germany, Springer, Heidelberg, (2004), pp. 127-140
Moerchen, F.: Analysis of speedup as function of block size and cluster size for parallel feed-forward neural networks on a Beowulf cluster, IEEE Transaction on Neural Networks 15(2)(2004), pp. 515-527 IEEE Xplore

2003

Moerchen, F.: Time series feature extraction for data mining using DWT and DFT, Technical Report No. 33, Dept. of Mathematics and Computer Science, University of Marburg, Germany, (2003)
 
Data:
IntervalsInterval time series data sets used in my publications on temporal pattern mining.
 
Code:
TSKMMatlab code for the Time Series Knowledge Mining algorithms of my PhD thesis. There is also a Java implementation by Michael Thies.
PersistMatlab code for the Persist time series discretization method.
ESOMJava code for training and visualization of Emergent Self-Organizing Maps (ESOM).
MusicMinerJava code to visualize music collections with maps such that similar songs are placed close to each other and different sounding songs are far apart or seperated by high mountains.
DWTMatlab code for the DWT time series feature extraction experiments.
BeowulfParallel training of feed forward neural networks on Beowulf cluster using MPICH and GSL.
 
Contact: Email to first name at this domain