Professional Documents
Culture Documents
Gerhard Viljoen: Top Skills
Gerhard Viljoen: Top Skills
Gerhard Viljoen: Top Skills
https://public.tableau.com/profile/cg.viljoen#!/
Top Skills
•
•
• Supervised Machine Learning (Neural Networks, Support Vector Machines, Random Forests, GBMs,
GAMs)
• Unsupervised Machine Learning (Market basket analysis, Self-organising maps, Multidimensional
scaling, Hierarchical Cluster analysis, Principal component analysis)
• Sentiment analysis, text classification, text generation
• Data Visualization (ggplot, R shiny apps, Infographics)
• Advanced Statistical Modelling: Monte Carlo & Bootstrap Methods, Bayesian inference
• Quantitative Image Analysis (Honours Thesis)
• SQL & NoSQL
• Bioinformatics
•
•
• Medical Science wet-lab skills (DNA Isolation, Cloning, Expression and Purification of Protein,
Stereology)
About me
I live and breathe out-of-the-box problem solving with an eye on rapid prototyping of statistically rigorous data
science solutions (https://rpubs.com/PsycheShaman/ ; https://github.com/PsycheShaman/MSc-thesis ) and putting these into production.
I always ensure that my work is delivered in easily digestible & visually stimulating ways
(https://public.tableau.com/profile/cg.viljoen#!/ ; https://create.piktochart.com/output/25685183-south-african-statistics-infographic ), in order to effectively
communicate actionable insights that drive real business value.
As an aside…
For the visually inclined, a more interactive version of my CV exists on Tableau public:
https://public.tableau.com/profile/cg.viljoen#!/vizhome/CV_123/ChristiaanGerhardusViljoen
Work Experience
2018 (CURRENT EMPLOYER)
Data Scientist / BCX, Cape Town
https://bcxecho.co.za
Developed various web app-embedded Tableau dashboards for the following companies, as part of a retail
insights suite in partnership with BCX Retail Connect’s Dolfin POS:
➢ AMIC Pty. Ltd. (Toys R Us & Reggies)
➢ Footgear
➢ Massbuild
• Combined agricultural sensor data, satellite- and geospatial data, to calculate agricultural measures
important in yield-forecasting, such as Heat Unit Accumulation per crop-type*
*Calculating Heat Units is a really interesting process, which involves numerical integration to find the area under an inverted sin curve,
forced through daily minimum- and maximum temperatures, and then doing ARIMA forecasting on the cumulative sum of heat units since
plant-date to predict stages in the life-cycle of various crop cultivars
• Utilizing the Decision Support System for Agrotechnology Transfer (DSSAT) to inform:
o Crop Simulation models for yield prediction
o Agricultural Management Practices Recommendations
Buckman Chemicals Project (On Consulting-basis for BCX Smart)
o Predicting Cobb levels, based on chemical variables measured on-site at paper mills, e.g. pH, First Pass
Retention, Conductivity, Particle Size, etc., using Generalized Additive Regression Models and a sum-of-
effects model
o Consulted with Buckman Chemicals employees on requirements
o Developed a Proof of Concept Interactive Web Application in R-shiny:
https://gerhard-viljoen.shinyapps.io/Cobb_App/
o Created lookup tables for front-end developers to customize look and feel for minimum viable product
https://buckman-ui-project.run.aws-usw02-pr.ice.predix.io/#
Hackathon
Placed first in an internal sales forecasting hackathon, which I won using an implementation of R’s
randomForest package
Supervision of Interns
o I supervised a WeThinkCode intern for 2 months during my consultation with BCX Smart IIoT
o I also concurrently supervised two teams of 5 Explore Data Science Academy interns for 6 weeks, doing
projects with The Foschini Group (TFG)
Ad-hoc Creative Work
o I designed Prezi presentation for a TFG DevFest Challenge we recently won
o I also produced a video outlining the solution: https://biteable.com/watch/tfg-challenge-option-2-
1894832/4fe291a3bb22521e24874141b7ac5dbb4e94b78b
o I designed a promotional flyer with QR code linking to a presentation of BCX Echo at an internal Sales
Conference
2017
Tutor / Teachme2, Cape Town
Afrikaans and Biology tutoring for primary- and high school students
2015 – 2016
Manager / Cash Crusaders, Rosettenville
Management of Merchandising and Storerooms, Staff Communication, OLX Ad Design and E-mail Marketing
2013
Buyer / Cash Crusaders, Rosettenville
Buying second-hand goods from the public, testing items, researching prices, negotiating buys. Sourcing additional buys from OLX and Gumtree.
2013
Auditing Fieldworker / PwC, Pretoria
Contract worker for the Department of Education's Infrastructure Audit. On-site infrastructure assessment of primary- and secondary schools in the
Ekurhuleni district, liaising with school principal regarding problems, recording results of reports on database.
Education
2017 - 2018
MSc Data Science / UCT, in progress
COURSEWORK (2017):
Database construction & management, statistical & high performance computing, data visualization,
unsupervised learning (market basket analysis, self-organizing maps, multidimensional scaling, cluster
analysis, principal component analysis); supervised learning (generalized linear models, tree-based methods,
multivariate methods, neural networks, support vector machines), Bayesian modeling, as well as the
application of these techniques to Astronomy, Particle Physics, Finance and other areas.
THESIS (2018-2019):
o The Application of Machine Learning Techniques towards the Optimization of High Energy Physics Event
Simulations in the ALICE TRD at CERN: https://github.com/PsycheShaman/MSc-thesis
2014
BSc (Med) (Hons) Bioinformatics / UCT
70%
THESIS:
"Feature Extraction from a 3D-Image Stack”
MODULES:
Python Programming, Bioinformatics for High Throughput Biology, Neurodegeneration and -regeneration
2010-2012
BSc Human Physiology / UP
3rd year highlights [2012] 70.32%
Anatomical Histology Techniques
Cellular-, Developmental-, Immunological-, Industrial-, Exercise-, Nutrition-, Neuro, Patho-, and Integrated Human Physiology
Abnormal Psychology 3; including Qualitative Research Techniques and critical academic writing for the social sciences (Literature reviews, etc.)
2nd year highlights [2011] 62.29%
Awarded membership to Golden Key International Honours Society
(Membership #7664721)
Neuro-, Circulatory-, Lung-, Renal-, Acid/Base-, Digestive-, Reproductive-, and Endocrine Physiology
Gene and chromosome organization, Genetic analysis and manipulation, Population Genetics; including Genetics practicals Social- and
Develomental Psychology
Organic Chemistry
Biochemistry of Lipids, Proteins and Enzymes, Carbohydrates: (Molecular structures and physical properties, Metabolic Pathways, Integrated
Biochemistry, e.g. Absorption, Distribution, Metabolism and Excretion of Medicines); including Biochemistry practicals
Highschool
Matric / Hoërskool Dinamika, 2007