Aleksandra Deis

Aleksandra Deis

Data Scientist

Contact Me

About Me

I am a business analyst turned data scientist who is passionate about solving business problems by data-driven approaches.

Latest Projects


Echo

Recognition of Quick, Draw! doodle images

Research in recognition of images drawn by humans can improve pattern recognition solutions more broadly. Improving pattern recognition has an impact on handwriting recognition and its robust applications in areas including OCR (Optical Character Recognition), ASR (Automatic Speech Recognition) & NLP (Natural Language Processing). In this project, I analyzed the Quick, Draw! game drawings and built a deep learning application to classify those drawings.

Find out more

Download report

Kaggle Dashboards Project

Kaggle Dashboards Project

Flask web application to view dashboards demonstrating Kaggle activities. Data for dashboards is collected automatically using Kaggle API.

Find out more

Spark Music Service Project

Music Service Data Analysis with Spark

Predicting churn rates is a challenging and common problem that data scientists and analysts regularly encounter in any customer-facing business. It is crucial for businesses to identify customers who are about to churn and take action to retain them before it happens. The goal of this project was to help Sparkify music service retain their customers. In this project, I analyzed Sparkify data, built a machine learning model to predict churn and developed a web application to demonstrate the results.

Find out more

Download report

Other Projects

Kaggle Kernel Votes Analysis

I have recently joined Kaggle and started to create public kernels. My kernels have many views, but no upvotes. So I decided to analyze Meta Kaggle dataset to find out statistics for kernels, which obtained medals and how different factors affect the number of votes (for example, characteristics of the author, source dataset and so on)? Also, finally, make the recommendations on how to make the kernel useful so that other kagglers would cast upvotes.

Find out more

More on Medium

Generating Titles for Kaggle Kernels with LSTM

When I first found out about sequence models, I was amazed by how easily we can apply them to a wide range of problems: text classification, text generation, music generation, machine translation, and others. I got an idea to use Meta Kaggle dataset to train a model to generate new kernel titles for Kaggle. Kernels are the notebooks in R or Python published on Kaggle by the users. Kaggle users can upvote kernels. Depending on the number of the upvotes, kernels receive medals. Model, which generates kernel titles, can help to capture trends for Kaggle kernels and serve as an inspiration for writing new kernels and get medals.

More on GitHub

More on Medium

More on LinkedIn

Work Experience

Mentor on Data Scientist Nanodegree - Udacity (2019)

Mentoring Udacity Data Scientist Nanodegree students.

Data Scientist - Data Monsters (2017 - 2019)

Performed business analysis, feature engineering, modelling, and review of machine learning pipelines for various projects:

  • Performed business analysis and feature engineering for the prediction of court decision project.
  • Performed business analysis and review of machine learning pipeline for the prediction of the aortic valve implant project.

Business Data Steward - Sberbank (2018 - 2019)

Performed the analysis of financial data for building a data pipeline for real-time IFRS/MIS reporting. Analyzed over 700 attributes across various banking domains and designed the data processing pipeline.

Financial Services Consultant - Accenture (2013 - 2018)

Performed data analysis, conducted the data quality assessment (described the data quality metrics, data profiles, the rules for the data quality assessment):

  • Performed the analysis of marketing data, sales funnel, prepared recommendations for online sales channels optimization, and the business case for digital channels audit project in a TOP-5 Russian insurance company.
  • Developed system designs banking product selection engine for a TOP-3 Russian bank.
  • Developed system designs for internet banking application for a TOP-3 Russian bank.
  • Performed business analysis for Accounting Engine system project for a TOP-3 Russian bank.

More on LinkedIn

My GitHub

Loading the data.