Meinhard Ploner, Developer in Bruneck, South Tyrol, Italy
Meinhard is available for hire
Hire Meinhard

Meinhard Ploner

Verified Expert  in Engineering

Bio

Meinhard is a leader in data science and analytics with more than 15 years of experience. His strong background in statistics (a Ph.D.), ML, AI, and optimization allows him to see the overall picture and to design problem-specific algorithms, solutions, and visualizations. He's worked at Fortune 500 companies and startups and has also set up and led a team of data scientists. Meinhard joined Toptal to help customers in the creation of efficient and robust data-driven solutions.

Portfolio

GKN
HDFS, Apache Hive, Oracle, MongoDB, Docker Compose, Docker, PySpark...
BCG Digital Ventures
Amazon Web Services (AWS), Confluence, Trello, Jira, Python, R
ProSiebenSat.1 Digital GmbH
Amazon Web Services (AWS), Spark, Mixpanel API, MongoDB, Python, R

Experience

Availability

Part-time

Preferred Environment

SourceTree, Confluence, Slack, Visual Studio Code (VS Code), Jupyter, RStudio, Linux, Windows, MacOS

The most amazing...

...things I've built were two data-driven apps which saved the company a seven-digit amount of cost per annum and a platform for AI-driven automated trading.

Work Experience

Lead Data Scientist | Project Manager of Digital Transformation

2017 - PRESENT
GKN
  • Invented and implemented new algorithms for efficient 2.5D part nesting in additive manufacturing.
  • Advised other employees on statistics- and data science-related topics as well as created ad-hoc analyses, which sometimes led to the creation of dedicated data-driven applications.
  • Designed and implemented data-driven (web) applications, mostly using Shiny and the Docker stack.
  • Created machine learning pipelines working on three-dimensional data (3D).
  • Designed and created some very smart visualizations with a huge impact on the business value of the company.
  • Worked in the context of Industry 4.0 (IIoT). Certain pipelines had to deal with huge amounts of data (TBs).
Technologies: HDFS, Apache Hive, Oracle, MongoDB, Docker Compose, Docker, PySpark, RStudio Shiny, R, Python

Data Science Lead

2016 - 2017
BCG Digital Ventures
  • Set up the data science cohort and led a team of four data scientists.
  • Worked on innovation and incubation of ventures for DAX30 companies.
  • Traded off fast solutions (minimum viable solution) vs. sustainable solutions.
  • Led and hosted various topic discussions including product analytics, discrete optimization, as well as machine learning.
Technologies: Amazon Web Services (AWS), Confluence, Trello, Jira, Python, R

Senior Software Engineer of Product Analytics | Senior Data Scientist

2015 - 2016
ProSiebenSat.1 Digital GmbH
  • Improved the digital product by using data-driven product management and also refined the KPI system.
  • Designed and evaluated the results of a design of experiment (A/B test) including a sample size calculation and extensive scenario analysis.
  • Performed extensive research about data quality and set up a new tracking concept.
  • Worked with the big data team on a data platform based on big data Lambda architecture.
  • Coordinated the cooperation with the University of Bolzano (Prof. Ricci) for research on recommender system research stations; also co-authored a dedicated paper.
  • Oversaw and was in charge of topics related to data science, machine learning, and recommender systems.
Technologies: Amazon Web Services (AWS), Spark, Mixpanel API, MongoDB, Python, R

Senior Software Engineer | Mobile AR Expert

2011 - 2015
X-root Software GmbH
  • Designed, engineered, and architectured mobile software applications.
  • Led the technology for augmented reality (AR) applications.
  • Implemented a mobile app to monitor IT infrastructures.
  • Led data- and algorithmic-related topics and implementations.
Technologies: Blender, Unity3D, Android, iOS, Eclipse, Xcode, Java, Objective-C

CEO

2000 - 2015
Data-ploner.com
  • Analyzed ecological data using adequate methods (CCA, PCA) for the client: EURAC Research, Bolzano (I).
  • Implemented statistical algorithms for survival analysis and fractional polynomials. The R Packages logistf, coxphw, coxphf, and concreg are published on CRAN for the client: Institute CeMSIIS, University of Vienna (A).
  • Consulted and conceptualized different case studies for the BI project "GeoBI for the client" TIS Innovation Park (now IDM/NOI), Bolzano (I).
  • Conceptualized and implemented a mobile app for an online broker for the client: Brokerjet, Vienna (A); along with leading topics and implementations.
Technologies: Objective-C, Fortran, C++, R

Quant (Quantitative Analyst) — Alternative Investment and Quantitative Research

2002 - 2011
Erste Group Bank AG
  • Designed and invented new profitable trading systems. The implemented systems reach from intraday systems to long-term trading systems.
  • Designed and integrated a dedicated infrastructure allowing for parallel computing. This was then used to implement and simulate complex credit derivatives (CDO and ABS).
  • Worked on solutions for special financial problems and pricing of complex instruments.
Technologies: Distributed Computing, C++, R, MATLAB

An Unsupervised Learning Analysis on Countries Based on COVID-19 Data

In this project, I analyzed COVID-19 data by means of unsupervised learning. I used Python and Jupyter Notebooks to perform the analysis. Data was downloaded from the server of the John Hopkins University. I also imported data about the population sizes for all countries plus the states of the US and the provinces of China (sources: Worldbank and Wikipedia).
Having not an immense amount of data, careful feature engineering was performed to extract meaningful features for the machine learning step. The cluster analysis was conducted using some less-used methods: UMAP projection and HDBSCAN.
The analysis and its outcome are published on Towardsdatascience.com. The code is available on GitHub (Github.com/ploner/coronavirus-clustering).
1994 - 2002

Ph.D. in Statistics

University of Vienna - Vienna, Austria

JANUARY 2020 - PRESENT

Executive Data Science Capstone

Johns Hopkins University (Coursera)

MARCH 2017 - PRESENT

Discrete Optimization

The University of Melbourne (Coursera)

AUGUST 2015 - PRESENT

XSeries Big Data

University of California, Berkeley (BerkeleyX)

JANUARY 2015 - PRESENT

Process Mining

Eindhoven University of Technology (Coursera)

DECEMBER 2014 - PRESENT

Mining Massive Datasets

Stanford University (Coursera)

JUNE 2014 - PRESENT

Functional Programming Principles in Scala

École Polytechnique Fédérale de Lausanne (Coursera)

Libraries/APIs

PySpark, Keras, Mixpanel API

Tools

FreeCAD, MATLAB, Jupyter, Slack, Confluence, SourceTree, Xcode, Blender, Jira, Trello, Docker Compose

Languages

Python 3, R, C++, Objective-C, Java, Fortran, Python

Frameworks

RStudio Shiny, Spark, Unity3D

Paradigms

Agile Software Development, Functional Reactive Programming, Distributed Computing

Platforms

Docker, Amazon Web Services (AWS), iOS, MacOS, Windows, Linux, RStudio, Visual Studio Code (VS Code), Eclipse, Android, Oracle

Storage

MongoDB, PostgreSQL, Oracle RDBMS, Apache Hive, HDFS

Other

Machine Learning, Artificial Intelligence (AI), Data Visualization, Time Series Analysis, Supervised Learning, Unsupervised Learning, Experimental Design, Statistics, Statistical Analysis, Data Mining, Dash, Deep Learning, Scenario Analysis, Biometrics, Customer Lifetime Value (CLV), Optimization

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring