10 Acade my profile site

Kevin Christian ZANOU

Cotonou, Benin

Laboratoire de Biomathématiques et d’Estimations Forestières (LABEF) of University of Abomey-Calavi, Benin


Master degree in Biostatistics


Email: zchristian955@gmail.com

ETL/ELT

Python and R programming, SQL MySQL, NOSQL, Kafka, Spark, Airflow, AWS Redshift, DBT

TensorFlow, Keras, Scikitlearn, Mathplotlib , Rasterio.plot

Machine Leaning , Deep learning,Data visualization

Mathematics and Statistics

Algebra , Probability , Causal Inference, Bayesian statistic,




Others

GitHub ,DVC , Building ML dashboards, Travis CI ,pytest, Geostatistic




About me


  • A junior Data engineer and Data analyst, able to build data pipelines, data structures, algorithms with experience on AWS and to contribute with statistic tool for the delivery of new technology on data mining , visualization and analysis.

  • Looking to use my Bachelor of Science in Statistic to manage statistical model and data-related solutions at organizations. Self-driven, hardworking and teamwork looking to make an impact using technology. I am capable in Python and R programming, SQL programming , Data Extraction (Kafka), Data Transformation (ETL), machine learning software tools like tensorflow, keras, dvc, factormineR, ggplot2, random forest and mlflow data mining,data cleaning, analysis, visualization, interpretation of large datasets and develop models.














Education

  • 10 Academy (2021 -2021)

Training in data engineering and machine learning engineering.

  • Programming languages (Python , SQL)

  • SQL and NoSQL databases

  • Data Pipelines, ETL and Orchestration ( Airflow , Spark , Transforming data , Exploratory Data Analysis )

  • ML DevOps and CI/CD (Jenkins, Travis CI , DVC, Mlflow

  • Machine Learning (Generalized machine learning and optimization (TensorFlow, Scikitlearn, Pytorch)

  • Data Science Tools (GitHub , Jupyter notebook , Bash and other scripting tools (powershell, ssh etc)

  • Visualization and dashboarding (Streamlit)

  • Project Management (Reporting, documentation, Remote collaboration tools , Design thinking , Blogging)


  • Laboratoire de Biomathématique et d’Estimations Forestières (LABEF) of University of Abomey-Calavi, Benin

MSc.(Statistical Science option Biostatistic ) pending to defense

  • Statistical and machine learning models for inference and predictive analytics for parametric and non-parametric statistics.

  • Time series analysis, analysis of trend, seasonality, stationarity, ARIMA intervention analysis.

  • Generalized linear mixed model .Bayesian statistic , Linear mixed model , Species distribution modeling, Survival analysis, Dynamic of population( Structure of population modeling), Multivariate Analysis

  • Research methods, collecting, analyzing and presenting results.



  • Ecole Nationale d'Economie Appliquée et de Management (University of Abomey-Calavi)

Bachelor Degree in Statistic Economic


Work Experience

  • Statistician Assistant at Global Freedom Corporation (GF Coorporation) since

March 2021

  • Consultant Statistician at Global Freedom Corporation , working on project Annual

Performance Report indicators on behalf of the Ministry of Digital and Digitization , June to

September 2020

Projects

SmartAd A/B testing


Using A/B testing to test if the ads that the advertising company ran resulted in a significant lift in brand awareness .Comparing machine learning models vs A/B testing gave me that we cannot reject the null hypothesis,Since our p-value=0.449 is way above our =0.05, which means that, there is no difference in brand awareness between the exposed and control groups in the current case. That's also means that it is more likely that the brand awareness of the new design is similar to our baseline. This is further proof that the new design is not likely to be an improvement on the old design, and that unfortunately we are back.

Pharmaticula Sales Prediction

Predict daily sales in various stores up to 6 weeks ahead of time. Deep Learning techniques was used to predict various outcomes including but not limited to future sales.




USGS_LIDAR_AgriTech

LiDAR data collected by the US government and stored in AWS is used for different spatial applications including agriculture, urban planning and environmental applications.

In this project, agri-tech python package was built to access the freely available Entwine Point Tile (EPT) data for user defined co-ordinates, store and visualize it.


Breast Cancer Diagnosis

We apply machine learning techniques to the Wisconsin Diagnostic Breast Cancer (WDBC) data. The WDBC data is class labeled, hence it will be a classification problem. The data has two classes (B=Benign, M=Malignant) and 32 attributes, or features. By using Causal graph , we see that the "area_se" feature is exposure and has a causal effect on the breast cancer diagnosis.We computed also after that a Bayesian statistic .