Rain Padjus

← Back to list

middle

Registration: 17.03.2023

Specialization: Machine Learning Engineer

C++ Git Python SQL Matplotlib pandas PyTorch

Portfolio

Web dog CNN(92% accuracy )

Created a CNN-based web application to classify dog breeds with an accuracy of 92%

GAN

Developed a custom neural network library, featuring a dynamic computing graph. Utilized this library to successfully implement a Generative Adversarial Network model

NeedleDream(Online course)

Developed site for paid online course with 300+ users Conducted sentiment analysis on reviews and created analytical models from raw data Increased sales and customer satisfaction by 15% Improved metrics (CV1 +5%, CPC +8%) through clustering and social media analysis Increased completion rates by 15% and user satisfaction by 20% through engagement metric analysis

Skills

Data science

Machine Learning

Python

Work experience

DATA SCIENTIST

since 01.2022 - Till the present day |NeedleDream

Python, SQL, Scikit-learn, matplotlib, seaborn, Fastai

DATA SCIENTIST/ML ENGINEER

01.2021 - 01.2022 |Freelance/Toy projects

Python, SQL, Scikit-learn, matplotlib, seaborn, Fastai, Jupyter, C++

Created a CNN-based web application to classify dog breeds with an accuracy of 92% Developed a custom neural network library, featuring a dynamic computing graph. Utilized this library to successfully implement a Generative Adversarial Network model Customer Churn Prediction: Built a web-based tool to predict customer churn for a subscription-based service. Conducted sentiment analysis on customer feedback and created analytical models to identify key drivers of churn

Educational background

Computer science (Bachelor’s Degree)

2016 - 2020

Peter the Great St.Petersburg Polytechnic University(ISO)

Languages

RussianNativeEstonianUpper IntermediateEnglishAdvanced