Chinyemba Victor - Data Science
Resume:
Chinyemba Victor
Data Scientist
******.****.****@*****.***
Atlanta, United States
victor.shamiso github.com/chinyemba
Over 12 years in information and data management, and 7 years of experience in Machine Learning, Data Management, Data mining with large Structured and Unstructured datasets, performing Data Acquisition, Data Validation, Predictive modelling, and Data Visualization. Experience in - Data Management, and Predictive modelling in the oil and gas industry.
WORK EXPERIENCE SKILLS
Data Science Lead
BP
06/2013 – 02/2019
Houston, TX
PROGRAMMING: Python, R, SQL
DATA STORES: SQL and noSQL,
BP is a multinational oil and gas company headquartered in Houston, Texas. It is one of the world's seven oil and gas "supermajors", whose performance in 2012 made it the world's sixth-largest.
Achievements/Tasks
Team leader for the Information and Data Management Team in the Global Wells Organisation (GWO) in upstream BP Africa, Brazil, Australia, and Nova Scotia.
Business change lead, and coordinated the implementation of business solutions, such as SAP, Well Integrity Management Systems, Work Management tools, Data Management systems, and many more.
Provided basic information and data support and services relating to unstructured data working across all business teams within the Global Wells Organisation
Developed and maintained processes and supporting tools for information and data control.
Interfaced information and data control resources with partners, vendors, regulatory agencies, and other external bodies, keeping distribution contacts current.
Extracted data from well-logging systems (e.g. OpenWells, CasingWear, StressCheck, Well Cost, and Campos, among others) to build machine learning algorithms to solve various problems.
Built an Ensemble Learning Algorithm to predict whether or not there will be deviation at any given well depth in a drilling operation.
Used an MLP Neural Network to predict Torque and Drag in order to minimize/avoid well casing, and formation damage.
Processed huge datasets (over billion data points and 2 TB in size) for data association pairing and provided insights into meaningful data association and trends.
Used Python 3.0 (NumPy, SciPy, Pandas, SciKit-Learn, Seaborn, NLTK) and Spark 2.0 (PySpark, MLlib) to develop variety of models and algorithms for analytic purposes.
Used NLP techniques to do sentiment analysis using data from social media API
Built a topic model algorithm using LDA to extract topics from more than 400k documents.
data warehouse, data lakes
Version Control: GitHub
MACHINE LEARNING METHODS:
Classification, pattern recognition, regression, prediction, dimensionally reduction, recommendation systems, targeting systems, ranking systems. Support Vector Machine, Decision Trees, Random Forest, Gradient Boosting Machine (GBM), KNN, Naïve Bayes, Clustering. Text Mining for Natural Language Processing.
LIBRARIES: nltk, Matplotlib, NumPy, Pandas, Scikit-Learn,
Keras, statsmodels, Scipy, TensforFlow, Keras, PyTorch, CNTK, Deeplearning4J, ggplot2
ANALYTICAL METHODS:
Advanced Data Modeling, Forecasting time series Models, Regression Analysis, Predictive Analytics, Statistical Analysis (ANOVA, correlation analysis, t- tests and z-test, descriptive statistics), Sentiment Analysis, Exploratory Data Analysis, Capital/Project Justification and Budgeting, Machine Time to Failure Analysis. Predictive Modeling with Time Series (AR, MA, and ARIMA) and Facebook Prophet. Performed Principal Component Analysis(PCA) and Linear Discriminate Analysis for features selection on cluster analysis; Bayesian Analysis, Linear/Logistic Regression, Classification and Regression Trees (CART)
IDE: Jupyter Notebook, Spyder, Colab Notebook, R Studio
WORK EXPERIENCE
Data Scientist [Frontline Services]
University of Sussex
SKILLS
RDBMS: SQL, MySQL
06/2011 – 02/2013
Brighton, United Kingdom
NoSQL: Amazon Web Services
The University of Sussex is a public research university located in Falmer, Sussex, England.
Achievements/Tasks
Worked with staff from different departments of the University to ensure that clients (students) had a great experience.
Created an interactive Dashboard on the Exlibris Alma system so that staff would have visibility of what was happening and trends.
Was in charge of change management, especially one that affected user experience and staff that directly provide services to users.
Built machine learning models such as linear regression to solve problems.
Used Natural Language Processing to classify tweets into negative and positive sentiments.
Worked independently to develop models that addressed specific business problems related to customer care, marketing of services and machine error predictions (time to failure).
Coordinated digitalization of library resources, especially the collection of metadata from scanned documents.
Developed Decision Support Monthly Statistical reports to upper Management and did monthly presentations in meetings.
Research Assistant
Innovations for Poverty Action
DATA ACTIONS: Data query and data manipulation
DATA VISUALIZATION: Qlickview,
R, Excel Dashboards
PRESENTATIONS: Proven
capabilities to present technical findings to non-technical audiences.
Document Control
SOFTWARE TOOLS: SAP, Excel,
PowerPoint, Word, SPSS, Landmark Drilling Sotfwares, Maximo, SharePoint, Exlibris Alma
COLLABORATION: Interact cross- functionally with a wide variety of
people and teams.
Data Governance
COMMUNICATION: Ability to comprehend needs and concerns
and provide easy to understand solutions.
EDUCATION
Master of Science, Data Analytics
02/2008 – 05/2011
Luasaka, Zambia
University of Brighton
The Abdul Latif Jameel Poverty Action Lab is a global research center
working to reduce poverty by ensuring that policy is informed by scientific evidence.
Achievements/Tasks
Coordinated social experiments that were aimed at establishing and measuring the impact of government policies on its intended beneficiaries in Zambia (countrywide).
Developed data entry forms and rules in Stata and supervised the National Data Entry team.
Performed data quality checks, preliminary data analyses, and reporting, before passing on the data to the Principal Investigator (Prof. Ashraf Navah of London School of Economics).
Bachelor of Arts, Library and Information Studies
University of Zambia
Certificate in Project Management Essentials
The George Washington University
LANGUAGES
Create presentation slides and posters to help principal researchers present findings.
Collect and log experimental data, and managed the data entry team.
Used SPSS to do data visualizations, and descriptive statistical analysis.
Ensured that the research and experiments were in accordance with the laid down protocols and make decisions on what to do if at any point a research subject violated such protocols.
English
Native or Bilingual Proficiency
Swahili
Limited Working Proficiency
Portuguese
Professional Working Proficiency
Other 10+ African languages
Professional Working Proficiency
Contact: Professor Nava Ashraf – *.*******@***.**.**
Contact this candidate