Еліса

Elisa
Elisa Biloshysta
Biloshysta
Kyiv, Ukraine
[відкрити контакти](див. вище в блоці «контактна інформація»)
[відкрити контакти](див. вище в блоці «контактна інформація»)
LinkedIn

ㅡ
Skills
- Calculus

- Statistics

- Data Analysis with python (numpy, pandas, sklearn)

- Clusterization, Classification, Regression

- Excel/Google Sheets (pivot tables as well)

- postgresql

ㅡ
Education Sikorsky Kyiv Polytechnic Institute, IASA / Bachelor's degree
SEPTEMBER 2019-JUNE 2023

System analysis at Institute for Applied System Analysis
Main core: data analysis and process management

Coursera
- Supervised Machine Learning: Regression and Classification
- Microeconomics: The Power of Markets - Coursera 4V99M92JUU6B
- Econometrics: Methods and Applications - Coursera FNZHFS2FHXRY
- Fundamentals of Reinforcement Learning - Coursera W8WLC2CJ3V6G
- Introduction to Data Engineering - IBM 9GUY6H7W4MY4
- Python for Data Science, AI & Development - IBM WQ9MX6KSJ99A E
Work experience Operations Specialist at Solidgate
SEPTEMBER 2023-NOVEMBER 2023
- Strong hands-on experience with Databases and SQL in DataGrip
- Data analysis in Google Sheets
- data analysis using excel(lookup functions and pivot tables
including) and sql
- automatization of database cleaning process (searching for
outdated data, dublicates or irrelevant data)
- new clients technical onboarding
- creating weekly reports for a company’s client using sql
- communication in English with business partners’ teams

Specific . Developed and implemented a strategic campaign optimization project to
experience maximize profitability by optimizing Cost per Install (CPI) for a mobile app
example company over a two-month period.

. Conducted an in-depth analysis of app install data and Lifetime Value
(LTV) from various publishers using the K-means clustering method to
identify distinct groups and facilitate effective campaign separation.

. Utilized both built-in iterative methods in Python and analytical
approaches, such as derivative analysis, to optimize CPI in two different
ways, ensuring a comprehensive exploration of the best possible
outcomes.

. Employed the K-means clustering algorithm to separate the publishers
into multiple campaigns based on their similarities, guaranteeing that
each campaign consisted of at least five publishers.

. Created separate tables for each proposed campaign, outlining the
selected publishers and corresponding CPIs, while striking a balance
between cost-effectiveness and the potential for acquiring high-value
users.

. Successfully optimized the campaigns by strategically allocating the
marketing budget, leveraging both Python's iterative methods and
analytical approaches, and achieved significant revenue growth by
acquiring users with higher LTV, ultimately maximizing the overall profit
for the mobile app company.
Marketing Analyst.docx