Prem Raj Adhikari
Prem Raj Adhikari
Data Scientist

Hi ! I am a Data Scientist proficient in Big Data and Statistics with a PhD in Machine Learning and Data Mining and 7 years of experience in the analytics sector. Passionate about data analysis and extracting business relevant insights and recommendations from data. I am also a self-motivated team player with an aptitude and desire for continuous learning, professional development and keeping abreast of the latest technologies. Currently, I'm a data scientist at Turku Center for Disease Modeling at Institute of Biomedicine in University of Turku. I am a member of the Endomet Project where the primary focus is on using machine learning and data mining methods in biomarker detection and development diagnostic  tools for different stakeholders such as patients, clinicians and pathologists.

Education Highlights

Doctor of Science (Technology): 2011 - 2014
Research Area: Machine Learning and Data Mining.
Algorithms: Clustering, Classification, Probabilistic Modelling
Dissertation Title: “Probabilistic Modelling of Multiresolution Biological Data
Supervisor: Academy Prof. Samuel Kaski, Advisor: DSc (Tech.) Jaakko Hollmén
Completed: 21.11.2014, Grade: 4.21

Master of Science (Technology): 2008 - 2010

Degree Program: Machine Learning, Data Mining, Neural Networks, Proba-
bilistic Methods, Information Visualization. Grade: 4.55,

Thesis Title: “Mixture Modelling of Multiresolution 0-1 Data”.
Supervisor: Academy Prof. Samuel Kaski, Instructor: DSc(Tech.) Jaakko Hollmén. Grade: 5


Data Scientist (February 2015 - Now)

Project Plan: Extract meaning from large-scale heterogeneous data, investigate biomarkers for disease; develop and commercialise disease diagnosis, prognosis, and follow-up software using powerful machine learning and data mining algorithms. The project resulted in disease diagnosis software (webtool) for clinicians, patients, and surgeons, which is currently under trial at a hospital.

Key responsibilities:

  • Optimised and applied state-of-the-art machine learning, data mining, and analysis methods in disease diagnosis

  • Revealing and visualising the structure of heterogeneous data by clustering

  • Identifying and validating biomarkers (Feature Selection) for disease diagnosis. Identified 10 robust markers from tens of thousands of variables. A notification of invention (patent) to the patenting organisations is submitted

  • Predicting the follow-up medical status of the patients (disease, recurrence, infertility, pain). Prediction accuracy improved to over 93% for disease diagnosis, and over 85% for recurrence prediction. Human Accuracy is ~70%

  • Acted as a project manager working closely with different stakeholders such as biologists, clinicians, software developers, business persons, and patients to ensure the project meets the business needs

Machine Learning Researcher (August 2009 - February 2015)

Projects: The project encompassed large-scale machine learning challenges in different application domains; with a focus on learning models from differently represented heterogeneous data collections.

Key responsibilities:

  • Identifying, investigating, and analysing current state-of-the-art statistical data analysis methods
  • Responsible for designing, implementing and evaluating the proposed solutions for data analysis and visualisation
  • Creating, adopting, and implementing new algorithms and methods ensuring high quality research
  • Collaborating with researchers and application area specialists to formulate and document project requirements and plans
  • Creating user requirements and feasibility study documents for the project, finalising the documentation to be published as conference proceedings, journal articles, technical reports, and theses for knowledge dissemination
  • Acting as a central reference and information source, providing assistance for timely completion of the collaborative project

Teaching Assistant (August 2011-February 2012 )

Key responsibilities:

  • Assisting Prof. Erik Aurell in organising the post–graduate course Quantitative Systems Biology
  • Preparing course materials, updating and maintaining course web-page
  • Organising and lecturing the tutorial sessions and reviewing assignments


For detailed list of publications please visit the publications page.
Research Visit

I visited The Delft Bioinformatics Lab at Delft University of Technology for two weeks from 5th to 17th of December 2011. I worked under the supervision of Assistant Professor Jeroen de Ridder on scale space theory and their application to genes. A longer visit is also planned for again sometime in the future. While in Delft, I gave a talk on my current work and future plans to the group.

I visited Department of Knowledge Technologies at Jožef Stefan Institute for a week from 16th to 20th of September 2013. I worked under the supervision of Professor Nada Lavrač on semantic data mining methods and their application to biological datasets. While in Ljubljana (JSI), I presented my current work and future plans for collaboration to the research group.

Academic Activities

2016: Program Committee Member, The 29th International Symposium on Computer-Based Medical Systems (CBMS 2016) held in Dublin (June 20, 2016) and in Belfast (June 21 – 23, 2016)
2012: Local Organising Team, The Eleventh International Symposium on Intelligent Data Analysis (IDA 2012) held between 25th and 27th October, 2012 in Helsinki, Finland.
2012: Academic Tutor of the students (Admitted Fall 2012) of Master's Programme in Machine Learning and Data Mining (Macadamia), Espoo, Finland
2011: Volunteer, The 14th International Conference on Discovery Science (DS 2011) held between 5th to 7th October, 2012 in Espoo, Finland
2011: Volunteer, The 21st International Conference on Artificial Neural Networks, Espoo, Finland

Get in Touch

Knowledge and Skills

Data Science

Algorithms and methods in data mining: itemset mining, randomization, rule learning, semantic data mining

Machine Learning

Classification, Clustering, Regression, Probabilistic Modeling


Implementation of machine learning and data mining algorithms. Includes data visualizations implements

Bash/Shell Scripting and awk

Data preprocessing

Database and SQL

Designing and maintaining RDBMS, updating the data in the database, retrieving and querying data from the database


Implementing various systems

Big Data

Proficient in Big Data Technology

About Prem

Prem Raj is a Data Scientist by trade and training, and a Post Doctoral Researcher at the University of Turku, Finland. He designs and develops algorithms, tools, and methods to make sense of vast amount of data.