In 2023, the prevailing product category purchased on social media in the United States was apparel. As indicated by a survey, 25.6 percent of users reported this category as their primary choice for making purchases on social networks. Following closely were beauty products and home goods, with 19.4 percent and 13.5 percent of respondents favoring these respective categories.

According to a survey conducted in Southeast Asia from June to August 2024, around ** percent of respondents reported having purchased beauty items due to recommendations from an influencer or celebrity. In comparison, around ** percent of respondents said they had purchased products in the travel category based on an influencer or celebrity's recommendation.

Product Sku Classification

## Overview

Product Sku Classification is a dataset for object detection tasks - it contains Product Skus annotations for 314 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Between January 1 and June 14, 2023, fashion and accessories were featured more than any other product on Instagram posts among consumers in the United States. Almost ************* posts were related to fashion and accessory products in the examined period. Lifestyle products racked up *** million posts, whilst food and beverages were posted about on Instagram *** million times in the U.S. in the examined period.

About this Dataset

A downloadable product list for the top search results in the category of Appliances on Amazon

Category

Product Lists

Keywords

ecommerce

Row Count

1958

Price

$15.00

theory of planned behavior constructs of purchasing domestic and foreign products, product category, and consumer ethnocentrism

1) Data Introduction • The Grocery Sales Database is a retail dataset of relational tables of grocery store sales transactions, customer information, product details, employee records, geographic information, and more across cities and countries.

2) Data Utilization (1) Grocery Sales Database has characteristics that: • The data consists of seven tables, including product categories, city/country information, customer/employee/product details, and sales details, each of which is interconnected by a unique ID. • Sales data are linked to products, customers, employees, and regions, enabling a variety of business analyses, including monthly sales, popular products, customer behavior, and regional performance. (2) Grocery Sales Database can be used to: • Analysis of sales trends and popular products: It can be used to identify trends and derive best-selling products by analyzing sales by monthly and category and sales by product. • Customer Segmentation and Marketing Strategy: Define customer groups based on customer frequency of purchases, total expenditure, and regional information and apply them to developing customized marketing and promotion strategies.

Human-labelled products image dataset named “Products-10k", is so far the largest production recognition dataset containing 10,000 products frequently bought by online customers in JD.com, covering a full spectrum of categories including Fashion, 3C, food, healthcare, household commodities, etc. Moreover, large-scale product labels are organized as a graph to indicate the complex hierarchy and interdependency among products.

Citing: Yalong Bai, Yuxiang Chen, Wei Yu, Linfang Wang, Wei Zhang. "Products-10K: A Large-scale Product Recognition Dataset". [arXiv]

When asked about "Interest in product categories", most German respondents pick ****************** as an answer. ** percent did so in our online survey in 2025.

The E-commerce Product Dataset is a comprehensive collection tailored for the e-commerce sector, featuring a wide range of products from 16 main categories including shoes, hats, bags, furniture, digital products, jewelry, and more. With over 200k SKUs, this dataset is equipped with bounding boxes and category tags, making it a pivotal resource for product classification and inventory management.

Overview This dataset contains 100,000 records of retail store sales data from various outlets across India over the past 5 years (2019-2023). It includes information about customer purchases, product categories, sales, discounts, and profit margins across different regions and outlet types.

This dataset is useful for sales analysis, customer segmentation, trend forecasting, and machine learning applications in the retail industry.

Dataset Features This dataset consists of 21 columns:

1. Customer & Order Information Order ID – Unique identifier for each transaction Order Date – Date when the order was placed Ship Date – Date when the order was shipped Ship Mode – Shipping method (Standard Class, Second Class, First Class, Same Day) Customer ID – Unique customer identifier Customer Name – First name of the customer Last Name – Last name of the customer Segment – Customer type (Consumer, Corporate)
2. Store & Location Information City Type – Tier 1, Tier 2, or Village Region – North, South, East, or West State – Indian state where the purchase was made Postal Code – Postal code for the purchase location
3. Product Information Product ID – Unique identifier for each product Category of Goods – Product category (Furniture, Electric Appliances, Fruits & Vegetables, Household, Dairy, Fast Food) Sub-Category – Specific subcategories under each category Product Name – Randomized product names based on subcategory
4. Sales & Profit Information Sales – Purchase amount in Indian Rupees (₹) Quantity – Number of items purchased Discount – Discount applied (0% - 50%) Profit – Profit calculated after applying discount Possible Use Cases Sales Trend Analysis – Identify yearly and regional sales patterns Customer Segmentation – Analyze customer behavior across different demographics Market Basket Analysis – Find product associations using ML techniques Sales Forecasting – Predict future sales based on past trends Profitability Analysis – Assess store and product category profitability Why Use This Dataset? ✔ Large Dataset (100K rows) – Ideal for machine learning & analytics ✔ Multi-Year Data (2019-2023) – Enables trend analysis over time ✔ Retail Industry Focused – Useful for sales and marketing strategies ✔ Includes Discounts & Profits – Helps in financial modeling

License & Citation This dataset is provided for educational and research purposes. If you use it, please cite it accordingly.

Would you like me to provide a dataset-metadata.json file for Kaggle, which will make uploading even easier? 😊

In 2024, clothing was the most commonly bought e-commerce product category in Croatia, purchased by almost ** percent of online shoppers. Shoes and fashion accessories followed in the ranking, purchased by ** and ** percent of the respondents, respectively.

The dataset includes 22 projects and 1680 user stories

Duty Free Products Market Outlook

As of 2023, the global duty free products market size is valued at approximately USD 75 billion, with a forecasted growth to reach around USD 130 billion by 2032, exhibiting a compound annual growth rate (CAGR) of 6.5%. This robust growth is primarily driven by the increasing international travel and rising disposable incomes, particularly in emerging economies. Duty-free products are becoming integral to the travel retail segment, contributing significantly to the overall market expansion.

One of the primary growth factors for the duty free products market is the surge in international travel. With globalization and the easing of travel restrictions post-pandemic, more people are traveling for leisure and business, leading to increased footfall in duty-free shops. Airports, seaports, and train stations are capitalizing on this trend by expanding retail space and enhancing the shopping experience for travelers. The availability of premium and exclusive products at competitive prices in duty-free outlets acts as a significant pull for consumers.

Another notable factor fueling the growth of the duty free products market is the rising disposable incomes in emerging economies such as China, India, and Brazil. As the middle class expands and purchasing power increases, there is a higher propensity to spend on luxury goods and high-end products. The allure of buying tax-free goods during international travel is particularly appealing to this demographic, driving sales in various product categories, including perfumes, cosmetics, and alcohol.

The advancement in digital technologies and e-commerce platforms also plays a crucial role in the market's growth. Duty-free retailers are increasingly adopting omnichannel strategies, integrating online and offline experiences to cater to tech-savvy consumers. Innovative marketing techniques, personalized shopping experiences, and seamless payment solutions are enhancing customer satisfaction and loyalty. Such advancements are expected to continue propelling the market forward.

From a regional perspective, Asia Pacific is anticipated to dominate the duty free products market during the forecast period. The region's growth can be attributed to the rapid economic development, increasing international tourism, and the presence of major global travel hubs such as Hong Kong, Singapore, and Dubai. Europe and North America also hold significant market shares due to their established travel infrastructure and high spending capacity of travelers.

Product Type Analysis

The duty free products market is segmented by various product types, with perfumes & cosmetics, alcohol & spirits, and tobacco goods being among the leading categories. Perfumes & cosmetics represent one of the most lucrative segments in duty-free retail. The demand for high-quality, branded beauty products is consistently high among travelers, making this segment a primary revenue generator for duty-free shops. The availability of exclusive products and limited editions that are not commonly found in domestic markets adds to the attractiveness of this category.

Alcohol & spirits is another significant segment within the duty free products market. The appeal of purchasing premium alcoholic beverages at tax-free prices is a strong motivator for travelers. This segment includes a wide range of products from luxury whiskies and fine wines to popular spirits like vodka and rum. The strategic placement of these products in duty-free outlets, often coupled with promotions and tasting events, enhances consumer engagement and boosts sales.

Tobacco goods continue to be a substantial segment despite regulatory challenges and increasing health consciousness among consumers. Duty-free shops often offer a diverse selection of tobacco products, including cigarettes, cigars, and smokeless tobacco, catering to a wide range of preferences. The tax-free pricing and availability of international brands make this segment particularly attractive to travelers who are habitual smokers.

Fashion & accessories, along with watches & jewelry, are growing segments within the duty free market. These categories are driven by consumers’ desire for luxury and branded items at competitive prices. Duty-free shops often stock the latest collections from high-end brands, making them popular shopping destinations for travelers looking to make premium purchases. These segments benefit from the trend of self-gifting and purchasing souvenirs for loved ones.

Prada web scraped data

  About the website

The Luxury Fashion Industry in the EMEA region, particularly in Sweden, is a thriving market with high demand for exclusive and high-end products. Prada, a renowned player in this industry, holds a significant presence. The industry is currently experiencing a significant shift towards digitalization and online retail, also known as Ecommerce, fueled by changing consumer behaviors and advancements in technology. A concrete example… See the full description on the dataset page: https://huggingface.co/datasets/DBQ/Prada.Product.prices.Sweden.

About this Dataset

Prodcuts data from https://manzzeli.com All products from the furniture category Last updated Dec 26 - 2022

Category

Product Lists

Keywords

furniture,egypt,furniture store

Row Count

6445

Price

Free

Manufacturer receives product number statistics (Class II environmental protection products)

Context

Product Sentiment Classification: Weekend Hackathon #19

Content

Analyzing sentiments related to various products such as Tablet, Mobile and various other gizmos can be fun and difficult especially when collected across various demographics around the world. In this weekend hackathon, we challenge the machinehackers community to develop a machine learning model to accurately classify various products into 4 different classes of sentiments based on the raw text review provided by the user. Analyzing these sentiments will not only help us serve the customers better but can also reveal lot of customer traits present/hidden in the reviews.

The sentiment analysis requires a lot to be taken into account mainly due to the preprocessing involved to represent raw text and make them machine-understandable. Usually, we stem and lemmatize the raw information and then represent it using TF-IDF, Word Embeddings, etc. However, provided the state-of-the-art NLP models such as Transformer based BERT models one can skip the manual feature engineering like TF-IDF and Count Vectorizers.

In this short span of time, we would encourage you to leverage the ImageNet moment (Transfer Learning) in NLP using various pre-trained models.

Acknowledgements

MachineHack

Attribute Description:

Text_ID - Unique Identifier Product_Description - Description of the product review by a user Product_Type - Different types of product (9 unique products) Class - Represents various sentiments 0 - Cannot Say 1 - Negative 2 - Positive 3 - No Sentiment

Amongst respondents who had previously participated in online video shopping events in the United States, over half (** percent) said that their favorite products to purchase in such events were items of clothing, while 17 percent answered electronics. Amongst non-watchers, clothing was also the most popular product category, with 29 percent. Notably, household goods were favored significantly more by those who didn't watch these events (** percent) than those who did (**** percent).

This dataset tracks influencer marketing campaigns across major social media platforms, providing a robust foundation for analyzing campaign effectiveness, engagement, reach, and sales outcomes. Each record represents a unique campaign and includes details such as the campaign’s platform (Instagram, YouTube, TikTok, Twitter), influencer category (e.g., Fashion, Tech, Fitness), campaign type (Product Launch, Brand Awareness, Giveaway, etc.), start and end dates, total user engagements, estimated reach, product sales, and campaign duration. The dataset structure supports diverse analyses, including ROI calculation, campaign benchmarking, and influencer performance comparison.

Columns: - campaign_id: Unique identifier for each campaign
- platform: Social media platform where the campaign ran
- influencer_category: Niche or industry focus of the influencer
- campaign_type: Objective or style of the campaign
- start_date, end_date: Campaign time frame
- engagements: Total user interactions (likes, comments, shares, etc.)
- estimated_reach: Estimated number of unique users exposed to the campaign
- product_sales: Number of products sold as a result of the campaign
- campaign_duration_days: Duration of the campaign in days

Getting Started with the Data

1. Load and Inspect the Dataset

import pandas as pd

df = pd.read_csv('influencer_marketing_roi_dataset.csv', parse_dates=['start_date', 'end_date'])
print(df.head())
print(df.info())

2. Basic Exploration

# Overview of campaign types and platforms
print(df['campaign_type'].value_counts())
print(df['platform'].value_counts())

# Summary statistics
print(df[['engagements', 'estimated_reach', 'product_sales']].describe())

3. Engagement and Sales Analysis

# Average engagements and sales by platform
platform_stats = df.groupby('platform')[['engagements', 'product_sales']].mean()
print(platform_stats)

# Top influencer categories by product sales
top_categories = df.groupby('influencer_category')['product_sales'].sum().sort_values(ascending=False)
print(top_categories)

4. ROI Calculation Example

# Assume a fixed campaign cost for demonstration
df['campaign_cost'] = 500 + df['estimated_reach'] * 0.01 # Example formula

# Calculate ROI: (Revenue - Cost) / Cost
# Assume each product sold yields $40 revenue
df['revenue'] = df['product_sales'] * 40
df['roi'] = (df['revenue'] - df['campaign_cost']) / df['campaign_cost']

# View campaigns with highest ROI
top_roi = df.sort_values('roi', ascending=False).head(10)
print(top_roi[['campaign_id', 'platform', 'roi']])

5. Visualizing Campaign Performance

import matplotlib.pyplot as plt
import seaborn as sns

# Engagements vs. Product Sales scatter plot
plt.figure(figsize=(8,6))
sns.scatterplot(data=df, x='engagements', y='product_sales', hue='platform', alpha=0.6)
plt.title('Engagements vs. Product Sales by Platform')
plt.xlabel('Engagements')
plt.ylabel('Product Sales')
plt.legend()
plt.show()

# Average ROI by Influencer Category
category_roi = df.groupby('influencer_category')['roi'].mean().sort_values()
category_roi.plot(kind='barh', color='teal')
plt.title('Average ROI by Influencer Category')
plt.xlabel('Average ROI')
plt.show()

6. Time-Based Analysis

# Campaigns over time
df['month'] = df['start_date'].dt.to_period('M')
monthly_sales = df.groupby('month')['product_sales'].sum()
monthly_sales.plot(figsize=(10,4), marker='o', title='Monthly Product Sales from Influencer Campaigns')
plt.ylabel('Product Sales')
plt.show()

Use Cases

• ROI Analysis: Quantify the return on investment for influencer campaigns across platforms and categories.
• Campaign Benchmarking: Compare campaign performance by type, influencer niche, or platform.
• Trend Analysis: Track engagement, reach, and sales trends over time.
• Influencer Selection: Identify high-performing influencer categories and campaign types for future partnerships.