Joonas Kauppinen

I am an analytic and creative thinker, eager to develop and learn new technologies. I have 15+ years of experience in statistical data analysis, including descriptive analytics, hypothesis testing, machine learning, optimization, probability, and regression. I am also a PhD student at Tampere University, Finland.

Contact information


firstname dot lastname at tuni dot fi

Core skills and research interests

Industry knowledge:

Algorithm design, analytics, artificial intelligence, big data, big data analytics, computer science, content management, data analysis, data mining, data presentation, editing, financial analysis, hypothesis testing, information retrieval, machine learning, mathematics, music composition, music information retrieval, music production, music theory, optimization, pattern recognition, probability, programming, regression, research, science, signal processing, statistical data analysis, statistical inference, statistics, writing

Tools and technologies:

C, HTML, Java, LaTeX, Matlab, Microsoft Excel, Microsoft Office, Python, R, SPSS, SQL

Interpersonal skills:

Collaboration, creativity skills, critical thinking, listening, presentations, problem solving, teaching


Finnish (native proficiency), English (full professional proficiency), Swedish (limited working proficiency), Japanese (elementary proficiency)


Joonas Kauppinen. Self-similarity matrix modeling using the nonnegative matrix factorization. In Antti Niemistö, editor, Digest of TISE Seminar 2013, volume 12 of TISE Publications, pages 21–26, Tampere, Finland, 2013. Tampere Doctoral Programme in Information Science and Engineering.

Joonas Kauppinen. The R Student Companion by Brian Dennis. International Statistical Review, 81(2):309, 2013. (doi:10.1111/insr.12020_3)

Joonas Kauppinen, Anssi Klapuri, and Tuomas Virtanen. Music self-similarity modeling using augmented nonnegative matrix factorization of block and stripe patterns. In Proc. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, New Paltz, NY, 2013. (PDF, 214322 bytes) (doi:10.1109/WASPAA.2013.6701855)

Self-similarity matrices have been widely used to analyze the sectional form of music signals, e.g. enabling the detection of parts such as verse and chorus in popular music. Two main types of structures often appear in self-similarity matrices: rectangular blocks of high similarity and diagonal stripes off the main diagonal that represent recurrent sequences. In this paper, we introduce a novel method to model both the block and stripe-like structures in self-similarity matrices and to pull them apart from each other. The model is an extension of the nonnegative matrix factorization, for which we present multiplicative update rules based on the generalized Kullback–Leibler divergence. The modeling power of the proposed method is illustrated with examples, and we demonstrate its application to the detection of sectional boundaries in music.

Joonas Kauppinen. Content-based data mining of musical scores. In Antti Niemistö, editor, Digest of TISE Seminar 2012, volume 11 of TISE Publications, pages 74–78, Tampere, Finland, 2012. Tampere Doctoral Programme in Information Science and Engineering.

Joonas Kauppinen. Music Data Mining edited by Tao Li, Mitsunori Ogihara, George Tzanetakis. International Statistical Review, 80(1):189–190, 2012. (doi:10.1111/j.1751-5823.2012.00179_13.x)

IEEE-copyrighted material: Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.