The aim of this study is to analyze the data from the Asos E-Commerce Dataset, which contains information on over 30,000 clothing items collected from the Asos website using web scraping. This dataset is a text classification dataset and can be applied in e-commerce analytics in the fashion industry. It is similar to the SheIn E-Commerce Dataset For each item in the dataset, the following attributes have been extracted: url: link to the item on the website; name: item's name; size: sizes available on the website; category: product's category; price: item's price; color: item's color; SKU: unique identifier of the item; date: date of web scraping, for all items - March 11, 2023; description: additional description, including the product's brand, composition, and care instructions, in JSON format; images: photographs from the item description; The aim of this study is to conduct data analysis, visualize key characteristics, build machine learning models to forecast demand for products, and identify the most important factors influencing demand The next steps include data analysis, machine learning model building, and conclusions based on the research findings

Our task involves conducting a fashion trend analysis and market sentiment analysis to support strategic decisions for a fashion brand startup. The goal of the research is to prevent potential errors in trend selection, sizing, and pricing, as well as to identify key factors influencing the success of products in the fashion market Product Name: The name of the product Price: The price of the product Brand: The brand of the product Category: The category to which the product belongs Description: A brief description of the product Rating: The rating assigned to the product Review Count: The number of reviews the product has received Style Attributes: The style attributes associated with the product Total Sizes: The total number of sizes available for the product Available Sizes: The sizes currently available for purchase Color: The color of the product Purchase History: Historical purchase data related to the product Age: Age demographic information Fashion Magazines: Mentions of the product in fashion magazines Fashion Influencers: Mentions of the product by fashion influencers Season: The season for which the product is suitable Time Period Highest Purchase: The time period during which the product experiences the highest purchase activity Customer Reviews: Customer reviews of the product Social Media Comments: Comments about the product on social media platforms Feedback: Feedback received from customers This dataset provides information about products from various fashion brands, including their characteristics, prices, ratings, reviews, and sizes. Analyzing this data will allow us to identify current fashion trends, consumer preferences, and optimize the assortment and pricing for our startup

В данном портфолио представлены возможности работы алгоритмов с изображениями. Для разных задач были выполнены следующие действия: - Сбор данных (текст или изображения) - Анализ полученных данных с использованием машинного обучения в зависимости от задачи - Генерация промтов на базе результатов аналитики - Генерация изображений по полученным промтам