Data Scientist Machine Learning

Bukola Oladele

+234**********, ****************@*****.***

LinkedIn GitHub

SUMMARY

I am a skilled data scientist with a passion for transforming complex data into actionable insights. My robust technical background includes proficiency in Python, C, and machine learning frameworks, which I have employed to drive impactful solutions across various projects. SKILLS

● Languages: Python

● Backend: Flask

● Libraries: NumPy, Pandas, Scikit-learn, TensorFlow, PyTorch.

● Databases: SQL

● Testing: A/ B Testing

Soft skills: Problem solving skills, Ability to work both independently and in a team, Delivering quality code for actionable insights

In a developer role at your company, I will:

● Collaborate and work closely with peers and mentors

● Pursue constant learning, growth, and improvement.

● Empower others, and build on success.

● Incessantly learn, grow and improve.

TECHNICAL PORTFOLIO

Atari Games Live I github

The project involves building an AI in Python that "plays" Atari video games using reinforcement learning and showcasing the power of DQN in autonomous gameplay.

Tech stack: Python, TensorFlow, OpenAI Gym, Deep Q-Network (DQN), Neural Networks.

● Build DQN agents from scratch watching as it gets trained to adept players in iconic Atari games

● Understand and implement the Deep Q-Network (DQN) algorithm mastering complex Atari games autonomously. Project 2 Live I github

Visa For Lisa

The project was to use a pre-existing dataset to help improve a customer marketing conversion rates by allowing them to target and predict better which of their deposit clients are most likely to accept a loan offer

● Tech stack: Python, NumPy, Pandas, Scikit-learn

● Data was collected, cleaned, explored and visualized using histogram, correlation matrix and scatter plot

● Fitted a logistic regression model on the training data, make predictions and calculate evaluation metrics such as accuracy, precision, recall, and F1 score.

Classically Punk Live I github

The project was to find a library that "reads" music files.

Tech stack: Os, Librosa, Python, NumPy, Pandas, Scikit-learn, Matplot, TensorFlow

● The dataset inform of audio snippet was converted to csv after defined features has been extracted in each genre(10)

● data and labels are put into training, validation, and test sets for machine learning model = Sequential, compiled by Adam optimizer and was trained for 100 epochs

My Paypal Live I github

The project was to build a fraud detection model that will identify fraudulent transactions and minimize the classification of legitimate transactions as fraudulent

● Tech stack: Python, NumPy, Pandas, Scikit-learn, Matplot

● Data was collected, cleaned, explored and visualized using histogram

● Logistic regression and RaindomForest Classifier models used on new data PROFESSIONAL EXPERIENCE

Data Science Intern(remote)

Qwasar Silicon Valley April 2023- present

EDUCATION

Outsource Global, OGTL

Data Science 2022- 2023

Contact this candidate