Marta Manevska's repositories
Big-Data-Kaggle-Dataset-Project
This report summarizes a big data project using a Kaggle dataset to predict review scores for orders in Brazilian marketplaces. We employed linear regression to identify key factors influencing review scores, including payment installment method, freight value, customer region, and payment type.
Business-Intelligence_SQL_Azure
The project examines factors influencing review scores in Brazilian e-commerce, analyzing payment methods, freight value, customer region, and delivery performance. Using big data and machine learning, it provides insights to improve customer satisfaction and logistics.
Data-Engineering
Customer aggregated data dataset provided by New Supermarkets International which was aimed to reveal data patterns, conduct customer segmentation and predict customer response to the subscription offer. Through data exploration negative entries in the customer spending column were revealed.
Data-Science-for-Marketing
Using PYTHON and CRISP-DM model for characterizing and describing the patterns of visitants of Portuguese attractions and comparing it to Portugal's main tourism competitors. Undrestanding visitors' frequent itemset associations, similarities between attractions or visitors, or segment visitors using RFM.
Google-Analytics-Project
As digital analysts with a background in using Google Analytics, we are excited to dive into the data from the tennis membership website and provide a technical and in-depth analysis of its digital performance over the period November 1st, 2021, to November 1st, 2022. Examination of different metrics.
Graph-Visualizations-Gaphi
By using Gephi’s modularity class feature, top 3 communities in subscription model were identified. No gender-related communities were detected. Based on centralities and hub measures there was found a list of users with efficient way transmitting information in the network, these top 100 users are recommended to target.
Machine-Learning-Techniques-Projects
Data Understanding, Data Preparation and Integration, Regression and Classification Modeling and Clustering Techniques.
Python-Sentiment-Analysis-Web-Scraping-
By utilizing web scraping techniques, we were able to observe the similarities and differences between both newspapers, when it comes to main keywords, topics, and even the sentiment expressed. How news outlets on both sides of the conflict portray the Ukrainian War, adding a third one that is supporting the Russian narrative in Europe.