The DataWeave Blog

Category: Counterfeit Detection

DataWeave’s AI Evolution: Delivering Greater Value Faster in the Age of AI and LLMs
In retail, competition is fierce, and in its ever-evolving landscape, consumer expectations are higher than ever.

For years, our AI-driven solutions have been the foundation that empowers businesses to sharpen their competitive pricing and optimize digital shelf performance. But in today’s world, evolution is constant—so is innovation. We now find ourselves at the frontier of a new era in AI. With the dawn of Generative AI and the rise of Large Language Models (LLMs), the possibilities for eCommerce companies are expanding at an unprecedented pace.

These technologies aren’t just a step forward; they’re a leap—propelling our capabilities to new heights. The insights are deeper, the recommendations more precise, and the competitive and market intelligence we provide is sharper than ever. This synergy between our legacy of AI expertise and the advancements of today positions DataWeave to deliver even greater value, thus helping businesses thrive in a fast-paced, data-driven world.

This article marks the beginning of a series where we will take you through these transformative AI capabilities, each designed to give retailers and brands a competitive edge.

In this first piece, we’ll offer a snapshot of how DataWeave aggregates and analyzes billions of publicly available data points to help businesses stay agile, informed, and ahead of the curve. These fall into four broad categories:
- Product Matching
- Attribute Tagging
- Content Analysis
- Promo Banner Analysis
- Other Specialized Use Cases
Product Matching

Dynamic pricing is an indispensable tool for eCommerce stores to remain competitive. A blessing—and a curse—of online shopping is that users can compare prices of similar products in a few clicks, with most shoppers gravitating toward the lowest price. Consequently, retailers can lose sales over minor discrepancies of $1–2 or even less.

All major eCommerce platforms compare product prices—especially their top selling products—across competing players and adjust prices to match or undercut competitors. A typical product undergoes 20.4 price changes annually, or roughly once every 18 days. Amazon takes it to the extreme, changing prices approximately every 10 minutes. It helps them maintain a healthy price perception among their consumers.

However, accurate product matching at scale is a prerequisite for the above, and that poses significant challenges. There is no standardized approach to product cataloging, so even identical products bear different product titles, descriptions, and attributes. Information is often incomplete, noisy, or ambiguous. Image data contains even more variability—the same product can be styled using different backgrounds, lighting, orientations, and quality; images can have multiple overlapping objects of interest or extraneous objects, and at times the images and the text on a single page might belong to completely different products!

DataWeave leverages advanced technologies, including computer vision, natural language processing (NLP), and deep learning, to achieve highly accurate product matching. Our pricing intelligence solution accurately matches products across hundreds of websites and automatically tracks competitor pricing data.

Here’s how it works:

Text Preprocessing

It identifies relevant text features essential for accurate comparison.
- Metadata Parsing: Extracts product titles, descriptions, attributes (e.g., color, size), and other structured data elements from Product Description Pages (PDP) that can help in accurately identifying and classifying products.
- Attribute-Value Normalization: Normalize attributes names (e.g. RAM vs Memory) and their values (e.g., 16 giga bytes vs 16 gigs vs 16 GB); brand names (e.g., Benetton vs UCB vs United Colors of Benetton); mapping category hierarchies a standard taxonomy.
- Noise Removal: Removes stop words and other elements with no descriptive value; this focuses keyword extraction on meaningful terms that contribute to product identification.
Image Preprocessing

Image processing algorithms use feature extraction to define visual attributes. For example, when comparing images of a red T-shirt, the algorithm might extract features such as “crew neck,” “red,” or “striped.”

Image hashing techniques create a unique representation (or “hash”) of an image, allowing for efficient comparison and matching of product images. This process transforms an image into a concise string or sequence of numbers that captures its essential features even if the image has been resized, rotated, or edited.

Before we perform these activities there is a need to preprocess images to prepare them for downstream operations. These include object detection to identify objects of interest, background removal, face/skin detection and removal, pose estimation and correction, and so forth.

Embeddings

We have built a hybrid or a multimodal product-matching engine that uses image features, text features, and domain heuristics. For every product we process we create and store multiple text and image embeddings in a vector database. These include a combination of basic feature vectors (e.g. tf-idf based, colour histograms, share vectors) to more advanced deep learning algorithms-based embeddings (e.g., BERT, CLIP) to the latest LLM-based embeddings.

Classification

Classification algorithms enhance product attribute tagging by designating match types. For example, the product might be identified as an “exact match”, “variant”, “similar”, or “substitute.” The algorithm can also identify identical product combinations or “baskets” of items typically purchased together.

What is the Business Impact of Product Matching?
- Pricing Intelligence: Businesses can strategically adjust pricing to remain competitive while maintaining profitability. High-accuracy price comparisons help businesses analyze their competitive price position, identify opportunities to improve pricing, and reclaim market share from competitors.
- Similarity-Based Matching: Products are matched based on a range of similarity features, such as product type, color, price range, specific features, etc., leading to more accurate matches.
- Counterfeit Detection: Businesses can identify counterfeit or unauthorized versions of branded products by comparing them against authentic product listings. This helps safeguard brand identity and enables brands to take legal action against counterfeiters.
Attribute Tagging

Attribute tagging involves assigning standardized tags for product attributes, such as brand, model, size, color, or material. These naming conventions form the basis for accurate product matching. Tagging detailed attributes, such as specifications, features, and dimensions, helps match products that meet similar criteria. For example, tags like “collar” or “pockets” for apparel ensure high-fidelity product matches for hard-to-distinguish items with minor stylistic variations.

Including tags for synonyms, variants, and long-tail keywords (e.g., “denim” and “jeans”) improves the matching process by recognizing different terms used for similar products. Metadata tags categorize similar items according to SKU numbers, manufacturer details, and other identifiers.

Altogether, these capabilities provide high-quality product matches and valuable metadata for retailers to classify their products and compare their product assortment to competitors.

User-Generated Content (UGC) Analysis

Customer reviews and ratings are rich sources of information, enabling brands to gauge consumer sentiment and identify shortcomings regarding product quality or service delivery. However, while informative, reviews constitute unstructured “noisy” data that is actionable only if parsed correctly.

Here’s where DataWeave’s UGC analysis capability steps in.
- Feature Extractor: Automatically pulls specific product attributes mentioned in the review (e.g., “battery life,” “design” and “comfort”)
- Feature Opinion Pair: Pairs each product attribute with a corresponding sentiment from the review (e.g., “battery life” is “excellent,” “design” is “modern,” and “comfort” is “poor”)
- Calculate Sentiment: Calculates an overall sentiment score for each product attribute
The final output combines the information extracted from each of these features, which looks something like this:
- Battery life is excellent
- Design is modern
- Not satisfied with the comfort
The algorithm also recognizes spammy reviews and distinguishes subjective reviews (i.e., those fueled by emotion) from objective ones.

Promo Banner Analysis

Our image processing tool can interpret promotional banners and extract information regarding product highlights, discounts, and special offers. This provides insights into pricing strategies and promotional tactics used by other online stores.

For example, if a competitor offers a 20% discount on a popular product, you can match or exceed this discount to attract more customers.

The banner reader identifies successful promotional trends and patterns from competitors, such as the timing of discounts, frequently promoted product categories or brands, and the duration of sales events. Ecommerce stores can use this information to optimize their promotion strategies, ensuring they launch compelling and timely offers.

Other Specialized Use Cases

While these generalized AI tools are highly useful in various industries, we’ve created other category—and attribute-specific capabilities for specialty goods (e.g., those requiring certifications or approval by federal agencies) and food items. These use cases help our customers adhere to compliance requirements.

Certification Mark Detector

This detector lets retailers match items based on official certification marks. These marks represent compliance with industry standards, safety regulations, and quality benchmarks.

Example:
- USDA Organic: Certification for organic food production and handling
- ISO 9001: Quality Management System Certification
By detecting these certification marks, the system can accurately match products with their certified counterparts. By identifying which competitor products are certified, retailers can identify products that may benefit from certification.

Nutrition Fact Table Reader

Product attributes alone are insufficient for comparing food items. Differences in nutrition content can influence product category (e.g., “health food” versus regular food items), price point, and consumer choice. DataWeave’s nutrition fact table reader scans nutrition information on packaging, capturing details such as calorie count, macronutrient distribution (proteins, fats, carbohydrates), vitamins, and minerals.

The solution ensures items with similar nutritional profiles are correctly identified and grouped based on specific dietary requirements or preferences. This helps with price comparisons and enables eCommerce stores to maintain a reliable database of product information and build trust among health-conscious consumers.

Building Next-Generation Competitive and Market Intelligence

Moving forward, breakthroughs in generative AI and LLMs have fueled substantial innovation, which has enabled us to introduce powerful new capabilities for our customers.

These include:
- Building Enhanced Products, Solutions, and Capabilities: Generative AI and LLMs can significantly elevate the performance of existing solutions by improving the accuracy, relevance, and depth of insights. By leveraging these advanced AI technologies, DataWeave can enhance its product offerings, such as pricing intelligence, product matching, and sentiment analysis. These tools will become more intuitive, allowing for real-time updates and deeper contextual understanding. Additionally, AI can help create entirely new solutions tailored to specific use cases, such as automating competitive analysis or identifying emerging market trends. This positions DataWeave to remain at the forefront of innovation, offering cutting-edge solutions that meet the evolving needs of retailers and brands.
- Reducing Turnaround Time (TAT) to Go-to-Market Faster: Generative AI and LLMs streamline data processing and analysis workflows, enabling faster decision-making. By automating tasks like data aggregation, sentiment analysis, and report generation, AI dramatically reduces the time required to derive actionable insights. This efficiency means that businesses can respond to market changes more swiftly, adjusting pricing or promotional strategies in near real-time. Faster insights translate into reduced turnaround times for product development, testing, and launch cycles, allowing DataWeave to bring new solutions to market quickly and give clients a competitive advantage.
- Improving Data Quality to Achieve Higher Performance Metrics: AI-driven technologies are exceptionally skilled at cleaning, organizing, and structuring large datasets. Generative AI and LLMs can refine the data input process, reducing errors and ensuring more accurate, high-quality data across all touchpoints. Improved data quality enhances the precision of insights drawn from it, leading to higher performance metrics like better product matching, more accurate price comparisons, and more effective consumer sentiment analysis. With higher-quality data, businesses can make smarter, more informed decisions, resulting in improved revenue, market share, and customer satisfaction.
- Augmenting Human Bandwidth with AI to Enhance Productivity: Generative AI and LLMs serve as powerful tools that augment human capabilities by automating routine, time-consuming tasks such as data entry, classification, and preliminary analysis. This allows human teams to focus on more strategic, high-value activities like interpreting insights, building relationships with clients, and developing new business strategies. By offloading these repetitive tasks to AI, human productivity is significantly enhanced. Employees can achieve more in less time, increasing overall efficiency and enabling teams to scale their operations without needing a proportional increase in human resources.
In our ongoing series, we will dive deep into each of these capabilities, exploring how DataWeave leverages cutting-edge AI technologies like Generative AI and LLMs to solve complex challenges for retailers and brands.

In the meantime, talk to us to learn more!
September 18, 2024
How AI-Powered Visual Highlighting Helps Brands Achieve Product Consistency Across eCommerce
As eCommerce increasingly becomes a prolific channel of sales for consumer brands, they find that maintaining a consistent and trustworthy brand image is a constant struggle. In an ecosystem filled with dozens of marketplaces and hundreds of third-party merchants, ensuring that customers see what aligns with a brand’s intended image is quite tricky. With many fakes and counterfeit products doing the rounds, brands may further struggle to get the right representation.

One way brands can track and identify inconsistencies in their brand representation across marketplaces is to use Digital Shelf Analytics solutions like DataWeave’s – specifically the Content Audit module.

This solution uses advanced AI models to identify image similarities and dissimilarities compared with the original brand image. Brands could then use their PIM platform or work with the retailer to replace inaccurate images.

But here’s the catch – AI can’t always accurately predict all the differences. Relying solely on scores given by these models poses a challenge in tracking the subtle differences between images. Often, image pairs with seemingly high match scores fail to catch important distinctions. Fake or counterfeit products and variations that slip past the AI’s scrutiny can lead to significant inaccuracies. Ultimately, it puts the reliability of the insights that brands depend on for crucial decisions at risk, impacting both top and bottom lines.

Dealing with this challenge means finding a balance between the number-based assessments of AI models and the human touch needed for accurate decision-making. However, giving auditors the ability to pinpoint variations precisely goes beyond simply sharing numerical values of the match scores with them. Visualizing model-generated scores is important as it provides human auditors with a tangible and intuitive understanding of the differences between two images. While numerical scores are comparable in the relative sense, they lack specificity. Visual interpretation empowers auditors to identify precisely where variations occur, aiding in efficient decision-making.

How AI-Powered Image Scoring Works

At DataWeave, our approach involves employing sophisticated computer vision models to conduct extensive image comparisons. Convolutional Neural Network (CNN) models such as Resnet-50 or YOLO, in conjunction with feature extraction models, analyze images quantitatively. This AI-powered image scoring process yields scores that indicate the level of similarity between images.

However, interpreting these scores and understanding the specific areas of difference can be challenging for human auditors. While computer vision models excel at processing vast amounts of data quickly, translating their output into actionable insights can be a stumbling block. A numerical score may not immediately convey the nature or extent of the differences between images

In the assessment of these images, all fall within the 70 to 80 range of scores (out of a maximum of 100). However, discerning the nature of differences—whether they are apparent or subtle—poses a challenge for the AI models and human auditors. For example, there are differences in the placement or type of images in the packaging, as well as packing text that are often in an extremely small font size. It is, of course, possible for human auditors to identify the differences in these images, but it’s a slow, error-prone, and tiring process, especially when auditors often have to check hundreds of image pairs each day.

So how do we ensure that we identify differences in images accurately? The answer lies in the process of visual highlighting.

How Visual Highlighting Works

Visual highlighting is a method that enhances our ability to comprehend differences in images by combining sophisticated algorithms with human understanding. Instead of relying solely on numerical scores, this approach introduces a visual layer, resembling a heatmap, guiding human auditors to specific areas where discrepancies are present.

Consider the scenario depicted in the images above: a computer vision model assigns a score of 70-85 for these images. While this score suggests relatively high similarity, it fails to uncover major differences between the images. Visual highlighting comes into play to overcome this limitation, precisely indicating regions where even subtle differences are seen.

Visual highlighting entails overlaying compared images and emphasizing areas of difference, achieved through techniques like color coding, outlining, or shading specific regions. The significance of the difference in a particular area determines the intensity of the visual highlight.

For instance, if there’s a change in the product’s color or a discrepancy in the packaging, these variations will be visually emphasized. This not only streamlines the auditing process but also enables human evaluators to make well-informed decisions quickly.

Benefits of Visual Highlighting
- Intuitive Understanding: Visual highlighting offers an intuitive method for interpreting and acting upon the outcomes of computer vision models. Instead of delving into numerical scores, auditors can concentrate on the highlighted areas, enhancing the efficiency and accuracy of the decision-making process.
- Accelerated Auditing: By bringing attention to specific regions of concern, visual highlighting speeds up the auditing process. Human evaluators can swiftly identify and address discrepancies without the need for exhaustive image analysis.
- Seamless Communication: Visual highlighting promotes clearer communication between automated systems and human auditors. Serving as a visual guide, it enhances collaboration, ensuring that the subtleties captured by computer vision models are effectively conveyed.
The Way Forward

As technology continues to evolve, the integration of visual highlighting methodologies is likely to become more sophisticated. Artificial intelligence and machine learning algorithms may play an even more prominent role in not only detecting differences but also in refining the visual highlighting process.

The collaboration between human auditors and AI ensures a comprehensive approach to maintaining brand integrity in the ever-expanding digital marketplace. By visually highlighting differences in images, brands can safeguard their visual identity, foster consumer trust, and deliver a consistent and reliable online shopping experience. In the intricate dance between technology and human intuition, visual highlighting emerges as a powerful tool, paving the way for brands to uphold their image with precision and efficiency.

To learn more, reach out to us today!

(This article was co-authored by Apurva Naik)
March 4, 2024
The Future of eCommerce is Social: Demystifying the Social Commerce Revolution
Social commerce is the selling of goods and services within a social media platform. Brands use social platforms such as Instagram, Facebook, Snapchat, and Twitter to promote and sell products. These platforms have become an integral part of consumers’ everyday life because they continue to engage users with relatable content, making them scroll their feeds for hours.

The Social Commerce model capitalizes on this high user engagement & moves social media beyond its traditional role in the top-of-the-funnel marketing process by encouraging users to shop without leaving their preferred apps. According to the Social Media Investment Report, 91% of executives agree that social commerce is driving an increasing portion of their marketing revenue, and 85% report that social data will be a primary source of business intelligence.

Let’s talk a little bit about why brands should consider selling via social media platforms:

Social Commerce vs. eCommerce vs. QCommerce

While they may fall under the same umbrella of online selling, social commerce, quick commerce, and eCommerce are three very different concepts
- eCommerce refers to online shopping via a (retailer or brand) website or app. Customers can access these platforms via desktop or mobile devices. However, the sales funnel generally looks the same. These brands and retailers use top-of-the-funnel tactics like social media content, digital ads, and other marketing strategies to encourage customers to visit the online store. There are three main types of eCommerce businesses: Business-to-Business (Alibaba, Amazon Business, eWorldTrade), Business-to-Consumer (websites such as Amazon, Rakuten, and Zalando), and Consumer-to-Consumer (platforms such as eBay & Etsy).
- Quick Commerce (or QCommerce) refers to eCommerce businesses that deliver goods within a couple of hours or even minutes. Although it’s sometimes used interchangeably with on-demand delivery or instant commerce, the idea of quick commerce has been around in the food industry for ages now. It has been recently ushered into the mainstream by evolving consumer preferences for quicker delivery of groceries and FMCG goods.
- Social commerce brings the store to the customer rather than redirecting customers to an online store. It removes unnecessary steps and simplifies the buying process by letting the customer checkout directly through social media platforms, creating a frictionless buying journey for the customer. Additionally, social media platforms are mobile-friendly, a huge benefit for brands because increasingly more and more customers are accessing the internet through mobile devices.
Social Commerce

Rise of Social Commerce

First used in 2005 by Yahoo!, ‘social commerce’ refers to collaborative shopping tools such as user ratings, shared pick lists, and user-generated content. Social media networks snowballed throughout the 2000s and 2010s, alongside a general increase in eCommerce, leading customers and merchants to quickly recognize the benefits of buying and selling through social media networks. Social media platforms have since evolved from merely a showcase tool for brands. They now serve as virtual storefronts and extensions of a company’s website or brick and mortar stores, capable of handling the buying experience.

Top Social Commerce Platforms

Social media platforms aim to keep visitors engaged on their platforms for as long as possible. Increased time in-app or on-site maximizes their opportunity to serve ads, a primary source of revenue generation. Social media platforms have millions of active users and they have a great power to help companies and individuals build their brands, interact with consumers, and support after-sales. Here are the top social commerce platforms:
- Facebook
Facebook introduced Facebook Shops to capitalize on the commercial opportunity by allowing vendors to advertise and sell directly through the platform. Facebook integrates social commerce with shopping, allowing users to purchase products smoothly. Facebook shops offer a smooth user experience where users can review products and get recommendations from trusted acquaintances. Customers can directly interact with the merchant’s customer service department post-purchase.
- Instagram
60% of people discover new products on Instagram. Owned by Facebook, Instagram facilitates in-app shopping and handles the entire transactions within the app itself. Users scrolling on Instagram often wants to follow trends and replicate the looks of their role models or favorite influencers. By offering purchasing options in the app, Instagram benefits from the platform’s rich visual imagery and videos, allowing businesses to sell an idea rather than the traditional process of selling a product.
- TikTok
Shopify partnered with TikTok to introduce shopping and drive sales through the younger and seemingly ever-expanding TikTok audience. With TikTok for Business Ads Manager, brands and merchants can create in-feed video-based content depending on their product offering. This partnership allows Shopify merchants to expand to the TikTok audience.
- Snapchat
Snapchat has recently launched Brand profiles, a feature that allows users to scroll through a merchant’s products and buy them in-app. This new experience is powered by Shopify too. Merchants can create Brand Profiles or Native Stores that allow users to purchase products from the app.

Pinterest users are there for Shopping Inspiration
- Pinterest
Pinterest is also an image-based platform where users create boards of their favorite wedding accessories, home decor, fashion trends, etc. Pinterest doesn’t specifically offer social commerce for the global audience. Rather, it allows business accounts to create ‘Product Pins’ that are displayed in the brand’s Pinterest shop. Only U.S. customers can purchase within the app. Users from other countries are redirected to the eCommerce site to complete the sale. We have added Pinterest to this list because 89% of Pinterest users are there for shopping inspiration.

Pinterest is an image-based platform where users create boards

Why Should Brands Care About Social Commerce
- To enhance social media presence and brand awareness
If your target demographic is in the 18-to-34 age range, they’re already on social media and waiting to shop while they scroll. According to Sprout Social, over 68% of consumers have already purchased directly from social media and nearly all (98%) consumers plan to make at least one purchase through social or influencer commerce this year. You can enhance brand awareness by selling on social media platforms. Influencer marketing is an amazing way to build brand awareness since customers are now seeking authenticity from micro-influencers rather than big-name celebrities.
- To generate social proof
90% of online shoppers say that they read online reviews before making an online purchase. Whether it’s an automated follow-up email or a message through the social media platform, ask for a review after your product has been delivered to the customer. You can also offer incentives like a contest to encourage previous customers to weigh in and share their experiences. These steps will allow you to collect social proof since it’s vital to build a positive reputation online. You can also ask customers to create small product review videos that you can share on your social feeds in creative ways. You can also post user-generated content, create a carousel of positive comments, or host a live video with happy customers.

Social Proof
- To simplify the buying process for consumers
Traditional eCommerce involves several steps. It starts with displaying ads on social media platforms and customers being redirected to the business website for completing the transaction. To complete the transaction, customers also have to create an account or manually fill in the credit card details and delivery address. On the other hand, social is only a three-step process — find, click and buy.

Counterfeit Products

Conclusion

While social commerce is proliferating, it also has a few setbacks like the rise of counterfeit products. Counterfeiting has expanded into social media and has become an under-reported but vital hub for counterfeiters. A counterfeit detection solution can help brands and merchants identify & remove fake and unauthorized products. Technologies like image recognition can help in counterfeit detection by capturing fake logos and discrepancies. Removing counterfeit products will help brands safeguard customer loyalty and prevent fake products from harming your bottom line.

Here’s how DataWeave helped Classic Accessories, a leading manufacturer of high-quality furnishings & accessories identify counterfeit products across multiple retail marketplace websites eliminating 22 hours of time spent per week conducting manual audits – read the case study here.

Are you a brand or a retailer worried about counterfeits? Sign up for a demo with our team to know how we can help you track, identify and eliminate fakes!
May 16, 2022
Importance of Image Recognition in the Retail Industry
When it comes to classifying and analyzing images, humans can easily recognize distinct features of objects and associate them with individual definitions. However, visual recognition is a highly complex task for machines because it involves identifying multiple objects and finding object relationships. Image recognition has been a long-standing research problem in the computer vision field. But, the recent development in AI has improved the process of object detection, image identification, and image classification. The image recognition market is assumed to rise globally to a market size of $42.2 billion by 2022. Various industries are adopting image recognition technology to improve augmented reality applications, optimize medical imagery, boost driverless car technology, predict consumer behavior, and much more.

Although image recognition is a relatively new aspect of analysis, it is also making its way into eCommerce. Image recognition is helping retailers to expand consumer reach, offer insights into trends, and improve customers’ online shopping experience for the eCommerce industry. The Global Image Recognition in Retail Market is estimated to be USD 1.8 Bn in 2021 and is expected to reach USD 4.5 Bn by 2026, growing at a CAGR of 20%.

Global Image Recognition in Retail Market

In this blog, you’ll learn about image recognition technology and its importance in the retail industry.

What is Image Recognition?

Image recognition, a subcategory of computer vision, is a technology that can identify objects, entities, or attributes in digital images or videos. However, computer vision is a broader term, including methods for gathering, processing, and analyzing data from the real world. Image recognition can be performed at varying degrees of accuracy, depending on the type of information required.

Image recognition can perform the following tasks:

Object Detection, Semantic Segmentation & Instance Segmentation
- Classification: It identifies the “class,” i.e., the category to which an image belongs. A picture can have only one class.
- Tagging: It’s a classification task but involves a higher degree of accuracy. Tagging can recognize several concepts or objects within an image, and there can be more than one tag assigned to a particular image.
- Detection and localization: This step helps locate object(s) in an image. Once the system locates the object in question, localization helps to place a bounding box around it.
- Segmentation: This is also a detection task but involves a higher degree of precision. Segmentation locates element(s) to the nearest pixel in an image.
- Instance segmentation: It helps differentiate multiple objects belonging to the same class.
Image Recognition in eCommerce and how it works

Nowadays, increasing competition and customer expectations are forcing online retailers to constantly monitor market dynamics wrt their pricing, promotion & product assortment in order to stay competitive. To get these insights, retailers need to match and compare their products against their competitors to see where the gaps are. That’s where product matching comes in.

Product matching refers to finding the same or similar products against a target universe of products from across the web, across multiple competing retailers. Product matching uses AI-based image recognition to determine product attributes, find patterns, and detect text, product price, shipping information, and so on.

Here’s how DataWeave’s AI-powered analytics platform uses image recognition & aggregates insights & data for retailers from across the web to provide a comprehensive view of the online competitive environment.

Image recognition use-cases in the retail industry

a. Attribute tagging

Attribute Tagging

Getting shoppers to your eCommerce platform is one thing and getting them to complete a purchase is a steeper hill to climb. If your platform can’t provide search results that match with customers’ requirements, they’ll get lost, grow frustrated, and drop off. Attribute tagging with image recognition allows eCommerce stores to automatically generate attributes for all products so customers can quickly find products they are looking for.

Tags allow users to filter products based on the categories they want to explore. Product tags include everything the customer might specifically search for — color, type, size, brand, use, design, fabric, discount, etc. For example, a dress could have tags like red, evening, midi, summer, long-sleeve, silk, summer sale, etc. When a user looks for midi dresses or long-sleeve dresses, products with these tags will show up.

b. Search by image

Visual Search

Visual Search allows users to look for similar products using a reference image from their camera roll or downloaded from the internet. The visual search feature also enables eCommerce businesses to implement image-based search into their software applications. It maximizes the searchable potential of their visual data.

Meanwhile, Gartner predicts a 30% increase in digital commerce revenue by 2021 for companies who start supporting visual and voice search on their websites and apps. The benefits of visual search include more personalized, easy product recommendations and enhanced product discovery.

c. Fashion trend analysis

Similarity Matching

Tapping into trending product categories is a goldmine for any eCommerce business. Having insights into trending categories and products means less competition on search engines, fewer ads, and intelligent pricing. All of which can boost any retailer’s margins. Image recognition technology provides information about colors, styling techniques, fabric textures, prints, and more to spark consumer demand. It works by scanning social media images to pinpoint trending attributes and predict fashion trends. For instance, while scanning images, technology understands that it’s seeing a photo of a color-blocked sweatshirt because it recognizes the product has a hooded neck, full sleeves, blocks of different colors, and even the type of fabric. This technology can analyze millions of images, helping retailers analyze the volume of color-blocked sweatshirts.

We do this seamlessly at DataWeave. Our similarity matching solution helps retailers gather insights into attributes for products similar to the ones they’re carrying on their site. Similarity matching helps retailers gain visibility into their entire competitive landscape to keep their e-commerce strategy responsive to price & product assortment shifts among consumers and rivals

d. Augmented reality

According to Statista, the AR market is valued at $9.5 billion, with around 810 million active mobile users. Since shoppers want the full sensory product experience before shopping online, augmented reality (AR) can help them understand what they’re buying and how the product will work for them. There are AR applications for trying makeup, clothing, accessories, and even eyeglasses. IKEA was one of the pioneers in using AR for eCommerce retail. In 2017, IKEA launched the Place app, allowing shoppers to see how thousands of items will look in their homes, with 98% accuracy.

Image recognition helps AR applications anchor virtual content with the real world. For instance, Sephora has a Virtual Artist that allows users to try different makeup looks and even take pictures of an outfit they’re planning to wear to match the shade. Users can even check out full-face looks and learn how to do their makeup with virtual tutorials.

e. Counterfeit Detection

Counterfeit Detection

Another application of image recognition that has proven to be very successful is counterfeit product detection. It has become increasingly difficult for brands and retailers to find and eliminate fake items on eCommerce sites. U.S. Customs seized over 13,500 counterfeit goods worth $30 Million in November 2021, indicating how brands and online marketplaces have struggled in the past to find an effective solution.

Essentially, image recognition technology allows eCommerce sites to detect products with fake logos and designs attempting to sell as legitimate brands by capturing discrepancies in images and content. The system flags and delists the products and sellers when a fake is detected.

Here’s how DataWeave helped Classic Accessories, a leading manufacturer of high-quality covers, furnishings, and accessories automate their counterfeit detection process using our super Image Recognition capabilities.

f. User-generated content analysis

Visual content plays a vital role in eCommerce sites, especially when it comes to product photos and videos. Today, branded visual content isn’t as effective as it’s one-dimensional. As a matter of fact, 93% of marketers agree that customers trust user-generated content more than content produced by brands. However, user-generated content that features product images or videos is way more exciting, realistic, and creative. It gives customers an appealing view of products being used in real life.

The most common form of UGC, i.e., reviews and ratings, have been the key for eCommerce brands as they are quantitative and qualitative metrics about a product/service quality, worth, value, reliability, etc. With image recognition, retailers can access insights into strengths and gaps in all product offerings by understanding what consumers are saying about them.

Here’s how DataWeave can help retailers and brands analyze consumer reviews & help them adapt to customer needs.

Conclusion

Because of its massive influence, image recognition technology is becoming widely adopted by eCommerce companies. It benefits both retailers and customers. Image recognition based on deep learning can provide retailers with helpful capacities like customer analytics, counterfeit detection, personalized searches, and more. Retailers can also use the data gathered from image recognition eCommerce technology to design effective marketing campaigns and improve their ROI.

With super sharp image recognition capabilities, DataWeave offers 90% accuracy in matching eCommerce products, allowing us to provide comprehensive and precise insights into pricing and assortments. Sign up for a demo with our team to know more.
December 20, 2021
Prioritizing Brand Protection Before the Holiday Rush

Counterfeits pose a dangerous threat to any retail brand. Since every single sale is a pivotal branding opportunity, especially for young, burgeoning eCommerce brands, an online marketplace flooded with counterfeits can be particularly dangerous. One in five customers will boycott a brand after mistakenly purchasing a counterfeit product, and that’s not the kind of ratio that any retailer –– from the smallest Direct-to-Consumer (DTC) site to the behemoths like Amazon –– can afford to ignore.

In the age of online reviews, it’s especially dangerous to have counterfeits floating around. Customers that have a bad experience with a counterfeit can take to the internet to disparage your brand without ever actually interacting with your company or trying your product. That’s why consistent and thorough content audits are paramount to ensuring your brand’s authentic products are highly discoverable, and brand protection and governance processes are in place to safeguard brand integrity across all applicable eCommerce websites.

The Holiday Counterfeit Boom

The holidays are a time when customers search for gifts for their friends and family, which means exploring brands outside of their usual fare. Many consumers will be exposed to your brand’s Digital Shelf for the first time over the holiday season, creating an opportunity for brand growth. But if you don’t have eCommerce brand protection initiatives in place, the holidays can be detrimental to brand positioning, customer trust, and your bottom line.

As consumers boost their online spending and web traffic increases over the holidays, so does the likelihood of them purchasing counterfeit goods online. eMarketer predicts that retail eCommerce sales will comprise almost 20 percent of total holiday retail sales this year. As such, there will also be a surge in counterfeit inventory. So, this is an ideal time to invest in a brand protection solution to help you stay ahead of unauthorized sellers entering the marketplace.

Brand Integrity Helps Suppliers Save

Implementing a solution to mitigate the risks of counterfeit products should be at the top of every retailer’s “To-Do” list this year. However, for many retailers, this means manually reviewing numerous websites and third-party marketplaces for violations. Not only is manually reviewing content, images, and seller authenticity a time-consuming process, but it also leaves a lot of room for human error – making it possible for counterfeits to slip through the cracks and into the hands of unsuspecting customers. Not to mention your time should be spent fulfilling orders and increasing customer satisfaction during the high-traffic holiday season, not distracted by monitoring counterfeits.

Fortunately, that’s not the only way to identify counterfeits and protect your brand online. An effective content auditing tool can help you monitor, detect, and determine systems to identify and act on identified violations, saving time and labor hours normally spent on manual auditing processes. Content audit software also often contains helpful features to help you run your business more strategically by monitoring online hygiene factors like product titles and description. It works across all online channels by highlighting content gaps, which can then be remedied to improve product visibility and conversions. Through online content optimization, you can save money (in unnecessary labor costs), improve your Share of Search, and increase sales and share, with a modest up-front investment.

Brand Value Protection Boosts Consumer Confidence

Brand image protection doesn’t just protect retailers, it also protects customers from unintentionally buying dangerous counterfeit goods. Counterfeiting has skyrocketed during the pandemic. The International Chamber of Commerce reports that, by 2022, counterfeit goods will be a $4.2 trillion industry, and global damage from counterfeit goods is projected to exceed $323 billion. Studies show one in four customers has unknowingly purchased a counterfeit item online.

As counterfeits increase in number, so does the risk of counterfeit consumption by unwitting consumers. Counterfeit goods are as dangerous as they are ubiquitous. Customs and Border Patrol has found ingredients such as cadmium, arsenic, lead, and cyanide inside of counterfeit cosmetics. Consumers are aware of these risks. So, as a retailer, you need to be able to reassure customers that they can trust the authenticity of the goods they are purchasing at your online store.

A counterfeit detection tool can help you identify fakes and image replicas across multiple online marketplaces, so you can get fake products delisted. Automated counterfeit solutions can increase customer satisfaction in their purchasing experience, since they know they’re getting an authentic product right off the bat. This type of online brand protection creates increased brand loyalty over time, as well as more positive first-time product interactions.

Making a Measurable Impact: A Counterfeit Detection Case Study

Classic Accessories is a leading manufacturer of high-quality furnishings and accessories. The company’s investment in a counterfeit detection tool paid off in spades for their organization. After noticing a surge in counterfeit versions of their goods being sold via online, global marketplaces, they decided they needed to change their manual counterfeit and image violation detection process to an automated one to proactively respond to concerned activity in a timely manner.

Their goal was to achieve streamlined, actionable insights across all retail websites to account for varied violation submission processes, and to reduce the timespan in which insights were generated, ultimately eliminating the need to conduct daily, manual audits. They partnered with DataWeave, who built out a fully customized program to automate Classic Accessories’ content inventory management process, and identified SKU-level violations by matching names and images in diverse online marketplaces.

During the first three months of onboarding, Classic Accessories was able to detect more than 25,000 violations, submitting notices to each marketplace, and even achieved a 100% removal rate across all Amazon sources. Additionally, they also achieved their goal of saving time (22 hours per week) in automation processes, translating to a $68,000 savings opportunity in labor costs.

Closing Thoughts

Prioritizing your online brand protection strategy is imperative to growing your online presence and achieving customer satisfaction and brand loyalty. Fortunately, there are options like DataWeave’s brand protection tool available to help curate your online content, provide consistency across online channels, and improve consumer confidence by addressing and removing counterfeit violations. Implementing the right solution can help find counterfeit products in real-time to keep your brand safe –– and your reputation intact –– throughout the 2021 holiday season. The right brand protection software will provide both Brand Protection and Content Audits, so your brand is optimized from every possible angle for truly competitive results.

October 29, 2021