Customer shopping habits have changed rapidly over the past decade. Customers today are looking for retailers that they can connect and engage with. Retailers must also change their marketing methods to interact with customers in an organic manner and provide an authentic brand experience.

One of the methods that is gaining popularity is the use of user-generated content (UGC). UGC is social media content created and shared between customers. Consumers want to be recognized for their input and as a result, retailers can benefit from the online discussion of their products. UGC can allow retailers to engage with their customers before, during and after a purchase. It provides customers with opportunities to promote the brands they like.

UGC in Marketing

UGC goes beyond mere likes or shares on social media. Customers often upload well-captured photographs or videos of the product. This content may even include comments and feedback about their experiences while using the product. Customers also leave reviews or offer recommendations of products they’ve purchased and used. UGC lets existing customers speak to future customers.

Given a choice between believing an advertisement by a retailer or a recommendation by another person, consumers tend to choose the latter. In fact, 93% of the consumers feel that UGC is helpful when making a purchase decisions.

Customers are continually bombarded by advertisements, but the impact is especially powerful when a customer feels a connection with another customer's experience. UGC works best when the message is real and authentic.

For example, cosmetics retailers benefit when their customers share pictures while wearing their products. Make-up artists are very popular on Instagram and they endorse the cosmetics brands they like. Followers of these make-up artists see these recommendations as credible and as a result, they are more likely to buy based on the recommendations. This user generated content showcases how the product works with a practical example, and without a heavy sell by the manufacturer/retailer. The result is that the credibility of the make-up artist is translated to the product and subsequently to the manufacturer/retailer.

UGC in Customer Retention

As a retailer, your job is to attract customers. However, it is equally crucial for you to nurture existing customers. How often are you creating rewards or special offers based on your customers purchase history? Have you considered utilizing UGC to showcase related or compatible products to existing customers?

You've made a big investment in attracting and nurturing your customer base. Don't lose it!

1. Find UGC for your products where ever it exists and get it in front of new customers. Let your existing customers and fans do some of the hard marketing work for you. 
2. Use social media to create an online community where users can discuss the products they’ve bought and offer recommendations to each other. Repost the best content on your official channels.
3. Encourage customers to discover and share multiple uses of a product. Use UGC to showcase the versatility of your products. This retains old customers while drawing in. Retailers can also hold events like sales to boost customer interaction.

Artificial Intelligence in Curation of UGC

UGC is a key element of a successful marketing plan. With the growth of social media, content is being created every second. This can become an invaluable resource. The problem is that most of this content is uncurated as it's published. 

Learn to leverage Artificial Intelligence (AI) to augment your marketing team. You can employ AI to curate UGC and use it for your benefit, by helping your human curation teams to curate faster and with higher accuracy. A side effect is that you can quickly become aware of product issues or bad publicity from a user review, and avoid the business risk associated with that. New ways of employing the content are coming out as the digital channels continue to diversify. You must curate UGC if you want to harness its power.

Trust is key. The conversations initiated by UGC can boost your bottom line. Nurture and reward your best content creators, and you'll see your customer base grow.

Of course with a growing customer base comes increased brand awareness, customer reach, and revenue.

 E-commerce has changed the way people shop, giving retailers and businesses new avenues to interact and engage their customers. Millennials are currently the most valuable target demographic for modern retailers. As they are also the most avid users of social media, a crossover was all but inevitable.  

Retailers, realizing the power of social media, have used these platforms for a while now to engage with their customers online. Social media also lets retailers market their products in a more interactive environment.

Recently, social media platforms like Instagram and Facebook have been investing in retail. This captures wide consumer interest and boosts both revenues as well as followers. As for retailers, they can use social media platforms to better understand consumer behavior and trends.

UGC or user-generated content is one of the most valuable data sources for retailers. Millennials put a lot of trust and faith in peer evaluation of products. Studies show that reviews and recommendations by fellow shoppers, rather than brand messaging, motivate customers to buy products online.

Here are a few instances of how social media platforms are leveraging the retail space:

Facebook Shop and Marketplace

​Facebook has a feature called Facebook Shop. Retailers can add the Shop tab to their business page. It lets retailers display their products and sell directly from their company page itself. Considering the huge number of users on Facebook, this offers retailers a wide audience to convert into customers. Retailers can upload a product catalog to their page and customers can browse the products and buy them without having to leave the page. It also allows retailers to manage orders, and mark them as shipped or canceled right on the page itself.

Facebook also introduced Facebook Marketplace, an online market for retailers to display products. This offers free organic distribution for retailers’ products. It curates content and provides product recommendations based on user preferences and relevance. This ensures higher conversion from a user to a consumer. Like Facebook Shop, there is no listing fee involved. It is an online platform for retailers to sell to their customers.

#Instashopping on Instagram

​Instagram is one of the most popular social media platforms with more than 1 billion active users; and about 60% or a whopping 600 million people, seek out and discover products on the app. Instagram has introduced shoppable posts which allow customers to go from discovery to buying without having to leave the app. Retailers can add up to 5 product tags per picture on business accounts only. They can only tag products from their Facebook Shop catalog. These tags redirect the customers to a product page that allows them to buy the products.

This seamless and hassle-free shopping experience has a wide appeal for the customers. In June 2018, they added Shoppable Stories which are an added advantage as about 400 million users view Stories every month. As of late 2018, Instagram also added a shopping channel to the Explore page, which is in its testing phase.

Shop and Cop by Snapchat

​Snapchat  has introduced ads and product catalogs through its self-service ad buying platform. Recently, they released a dedicated shopping channel called Shop and Cop on the app which will feature exclusive offers and limited time deals through Shopify. These channels will be available in the Discovery section of the Snapchat app. Shop and Cop will feature social influencer posts and content. Shopify capabilities will allow in-app purchases ensuring a smooth shopping experience without the user leaving the app. Snapchat will curate products while Shopify will take care of the buying end. Moreover, Snapchat and Amazon have announced a partnership on a visual search tool. This will allow customers to use the Snapchat camera to search for products on Amazon.

2018 saw a lot of innovations with social media intersecting with e-commerce to give the rise of social commerce.  Retailers stand to make big bucks off of these popular platforms by better understanding shopper purchase behavior and using it to their advantage. They can conduct market research, market their products better and even sell, all in one place. With these innovations, it's only a matter of time before social media takes over the world of retail.

From online shopping expanding to social media to customer-controlled delivery and returns, 2018 saw an exciting time in retail which drove a massive shakeup in the traditional retail landscape. Besides instant gratification, today’s connected customers expect newer experiences and hyper-personalization in retail. As we enter 2019, retailers are increasingly faced with the challenge to push boundaries and meet the evergrowing expectations of their customers.

Here are 5 retail trends that will gain momentum in 2019 -

Customer Datasets

Data plays a crucial role in the growth of any business. Accurate data will serve as a vital tool to enable retailers to understand customer behavior and reward their loyalty. This data will further enable retailers to deliver personalized shopping experiences to each customer. Retailers can target product offers more effectively due to access they have to customer datasets, AI and Machine Learning. Closer customer engagement will provide insights that can be valuable for retailers who want to grow their businesses. Forming stronger connections will be beneficial for both the customers and retailers.

Cognitive Technology

Cognitive Technology has led to automation across different parts of the retail sector, and this is a trend that will grow exponentially. Retailers will leverage cognitive computing to provide better customer service technology that can analyze enormous amounts of data. Retailers who integrate cognitive computing in their customer service can offer faster service. Setting computers and robots that can actually understand natural language and respond to simple questions will free up employees to attend to more complex queries. Robots can work alongside humans in many areas of retail increasing efficiency and productivity.

Voice-activated Shopping

As of 2018, Amazon and Google have together sold about 27 million voice-activated devices in the USA. 29% of these customers are already using the devices to shop online, and this number is slowly increasing day after day. Customers also expressed confidence in the recommendations provided by these digital assistants. These devices have a large following that can’t fully embrace their shopping abilities due to the lack of visuals. Companies are combating this by adding screens to their voice assistant devices. For example, Amazon Echo Show allows its users to view the products on the screen which increases confidence in their purchase.

Shopping anytime, anywhere

Consumers today are on the move and are going to expect services that could be available in transit. Social commerce will gain momentum by providing users/customers more choices for making purchases on the go. Retailers will be able to do targeted marketing and offer new ways to make online shopping more convenient, social and instantaneous. Customers will be able to shop from their vehicles while commuting. New innovative social commerce solutions will also emerge throughout 2019.

Augmented Reality

Augmented reality is quite popular with many apps that offer users a chance to blend the digital with the real world. These interactive experiences are not just fun but also offer retailers an opportunity to use them in shops. 

For example, if customers want to buy furniture, it could be quite difficult to picture the store items in their own house setting. If they pick wrong, they could end up ruining the aesthetics and ambiance of a room. Augmented reality apps can place 3D models of furniture right inside the customer’s home.

The digital furniture is also resizable and observable in any light, from any angle. Customers can even save room designs for the future. There is a huge level of customer engagement that can be achieved through these apps. They will allow customers to buy the best products and consequently come back to buy more in the future.

These trends may prove useful by providing retailers with some foresight. The landscape of the retail industry is evolving at a fast pace, and with Gen Z driving seismic shifts in shopping behavior, 2019 can be a very interesting year in retail.

Have you ever tried searching for a product on your favorite online shopping site, only to be disappointed when you couldn’t find the product that you’re looking for? Most product site search engines leverage accurate product categorization attributes to help narrow the search results for a user.

In this article we’re going to look at the impact that proper categorization has on search and how it’s now possible to automate product categorization with a machine learning model.

Categorization starts with a well designed product category taxonomy. The product taxonomy defines how each product type is related. The first couple levels of a product taxonomy contain broad category labels. For a grocery taxonomy, the top levels might be organized by departments within the store. It’s a logical representation of the way that a shopper would look for a given product in the physical store. A taxonomy is often referred to as a “Product tree”, with each product category referred to as a “branch” and each individual item referred to as a “leaf” on that branch.

Grocery taxonomy example:

1. Meat & Seafood

1. Fresh Meat

1. Ribs

2. Smoked Ham

3. Specialty Meat

4. Kosher Meat

5. ...

2. Fresh Seafood

3. Packaged Meat

4. Packaged Seafood

2. Produce

3. Deli

4. Bakery

5. Adult Beverages

6. Beverages

7. Floral

8. ...

For a new product to be put into the online product catalog, it first needs to be categorized appropriately into the correct level of the product taxonomy. This is easy enough for a human to complete the product categorization, however, when you have thousands and thousands of products, this can be a tedious process.

The science of search has evolved over the last two decades. Trying to determine the searchers intent from one or two words is not a simple process. We’re not going to dive into that in this article. However, in the specific use case of product search for an ecommerce website, most shoppers will generally include the object of their intent as part of the search input. In most cases this data can be used to quickly narrow the results set based on the product taxonomy. After all, the consumer isn’t looking for organic lettuce in the seafood section, nor would they be looking for seafood in the produce section. So one method to quickly close the search breadth is to narrow the search to specific sub-branch of the product taxonomy.

One downside to improper categorization is that improperly categorized products can become “lost”. When a product is mis-categorized on an improper branch of the taxonomy, the search engine may either (1) not find the product or (2) relegate the mis-categorized product to the bottom of the search results.

Don’t believe me? Try this: go to your favorite ecommerce provider, search for something, and then go to the last page of the search results. What do find there? Don’t let this happen to your product catalog.

In addition, the product category for a given catalog item can help define the product schema that should be employed to display the product information for the consumer on the product data page. The schema can also help define the meaning of generic product attributes, depending on the product type.

ATOM is the product categorization service from IceCream Labs. We developed ATOM as an API service which can be accessed automatically from your product information manager. ATOM takes a product title or description as an input and outputs the recommended product category for the item. ATOM is powered by a machine learning model that has been trained on millions of product records. It’s constantly learning as it processes new data.

With ATOM, you can properly categorize or validate a new product item before accepting it into your production product catalog.

To learn more about ATOM, or see a demo, contact our sales team: sales@icecreamlabs.com

PHOTO CREDIT: Photo by Min An from Pexels

Leveraging AI and Machine Learning for Product Matching

There is a vast number of products sold online through various outlets all over the world. Identifying, matching and cross-checking products for purposes such as price comparison becomes a challenge as there are no global unique identifiers.

There are many situations where accurately identifying a product match is essential. For instance, stores may want to compare competitor prices for the same product they may offer. Similarly, customers may use comparison tools to get the best deals. Amazon allows different sellers to offer the same products only after ensuring that they are the same before listing the sellers in a single, unique product page.

Numerous products but no method to match them across different stores

Product titles/descriptions do not have a standardized format. Each store, as well as different sellers within a store, might have different titles and descriptions for the same products. Another challenge comes in with respect to attribute listings as different e-tailers follow different formats. The product images of the same product also differ across different e-tailers.

While there are standardized unique identifiers like UPC, MPN, GTIN, etc, they, however, may not be mentioned in the product page in all stores selling them. The attributes themselves may be described differently - for instance 9" and 9 inches. Images may be included but they can differ in perspective, clarity, tone, etc. The brand name may also be referred to in different ways like GE and General Electric.

<image>

It is an impossible task for a human to visit different product pages to ensure if they are matching the same products. Although, if the process is to be automated, how can it be ensured that the system makes sense of all the information. This is when AI and machine learning come into the picture. 

Machine Learning for Product Matching

In machine learning solutions for product matching, the solution provider must initially build a database with billions of products. This can be done by collecting information through web crawls and feeds. The system then has to come up with a universal taxonomy. This especially is a unique challenge as different retailers use different classifications for their products, and the same product might be listed in more than one category. For instance, a particular shoe model might be listed under casual shoes as well as dress shoes. The system first must design a standardized taxonomy, irrespective of how a particular store classifies its products.

There are standard classification models such as Google Taxonomy, GS1, and Amazon but a product match solution may devise its own taxonomy. The universal taxonomy is designed by identifying patterns and signals from titles, product descriptions and attributes, and from images.

Once a universal taxonomy is in place, the next step is making particular product matches. Here, there is a need for precise comparisons to ensure a particular product is indeed the same unique product, despite the differences in titles, images, descriptions, etc. First, there is a search for unique identifiers such as UPC or GTIN on the product page. Then, the product titles need to be compared. It needs to be noted that no two product titles are the same across different stores for the same product, for example:

Neural networks play a key role

Neural networks and deep learning techniques are extensively used to identify and learn from similarities, to identify and learn from differences, and produce word-level embedding to create a system of representation for common words. This involves teaching the system to recognize different references to a unique entity such as 'GE' and General Electric or 7" or 7 inches, to come up with one unique representation for each entity.

A product can be identified using its title, description, images and attributes or its specifications list. In many cases, the product title itself will yield a lot of information and the system needs to be trained to differentiate the product name (for instance, brand model) from the attributes.

<Phone model images>Samsung Galaxy Note 8 (US Version) Factory Unlocked Phone 64GB – Midnight Black (Certified Refurbished)Samsung Galaxy Note 8 is the phone model, and the title provides additional information like the memory size, US version, Factory Unlocked Refurbished, etc. 

Identifying and sorting product matches 

The information then needs to be extracted and sorted into the appropriate slots - Phone model, version, memory size, etc. Different techniques might be used to help the system learn to parse and sort the different sets of information. 

The next comparison comes in the form of more information about the product such as the title, description containing additional information and a specs table. These help add more knowledge about the product, and the machine will be better able to identify an exact product match or mismatch in the following comparison.

The standard identifying signals are similar results or positive matches for unique identification numbers (UPC or MPN), classification, brand, title, attributes, and image. For each comparison, the system follows a long procedure of checks or safety valves. The checks pass through a search for the unique identification number, a test for keyword similarities, brand normalization and match (for example, HP is the same as Hewlett Packard), attribute normalization and match ( 9 inches is the same as 9in, 9"), image matching, etc. There is also a check for variation in attributes such as:

For the best product match result, there has to be at least 99% of positive results. It will be considered a mismatch, even if it is a variation of what is essentially the same product. Different product match solutions employ different techniques and training methods, and it is a complicated process. Although, there is an advantage that neural networks and machine learning learn over time, and get better with each use.

Speech Analytics vs Voice Analytics

Businesses today have access to more consumer data than ever before, especially through their customer support and service centers. The essence lies in understanding the optimal way of extraction and utilization of that data. Speech analytics and voice analytics are two approaches to call analytics that can be used for the same function. Even though they may both analyze phone conversations between customer support representatives and customers in order to reveal customer insights, their mechanisms are quite distinct. Discerning these differences is crucial to determine which solution of call analytics is ideal. Moreover, both the methods are used by customer support and service centers to gather information about the market performance of products. However, speech analytics and voice analytics are very different tools. The operating principles of analyzing used are very diverse.

Call Analytics

Call Analytics refers to the collection, measurement, analysis, and reporting of data collected over phone calls. Retailers and brands can use the insights gained from call analysis to optimize call handling and marketing campaigns. Call analytics also allow for viewing and analysis of both the macro and micro phone traffic patterns and sort the collected data into informative call reports. There are two different methods of call analysis, i.e speech analysis, and voice analysis.

Speech Analytics

Speech analytics analyzes the spoken content of a phone conversation by analyzing what is spoken between support representatives and the customers, and the context of the conversation. It does so by using phonetic indexing or converting speech to text for the organization of the content. Speech analytics makes it feasible to search and locate the speech of a representative or a customer and their response to each other. The context of the conversation is divulged by the method of isolating specific words and phrases in proximity to one another.For example, if a customer calls a business to ask about the shipment of an order and when it is expected to arrive, then the execution of a search for the words “order” and “shipment” of the customer with close proximity to a search of the customer care representative using the word “shipment,” crucial information such as the reason for the customer’s call as well as whether the customer received a satisfactory response may be determined.Important factors such as keywords and syllables based on a frame of reference searches set up by the business play a vital role in speech analytics. Unveiling the most common phrases and words used by customers during such a conversation enables speech analytics to give businesses better insights into the latest trends. This, in turn, prepares the business to be able to create informed marketing strategies and make decisions that provide the customers with the best experience possible.

Voice Analytics

In contrast to speech analytics, which focuses on the words and phrases used in an interaction between the representatives and the customers, voice analytics targets the intonation of how it was spoken. Voice analytics work by analyzing the audio patterns for vocal elements such as the tone, pitch, tempo, rhythm, and syllable stress,  to gauge emotional quotient. This provides businesses with a deeper knowledge of the mood of a customer.For example, if a customer uses the word “amazing”, voice analytics can be used for the detection of cues, such as anger or sarcasm, which utterly changes the meaning of the word. It is crucial to understand the demeanor of a customer in order to be able to provide them with a satisfactory experience.

After the assimilation of raw vocal data, it is run against an emotional voice database, comparing factors generated by the voice analytics system with known factors associated with emotions such as anger, happiness, fear, and sadness, to correctly identify and classify the emotional state of the customer. In essence, voice analytics captures the emotional aspect of speech in a conversation.

Speech analytics is essential in cases where specific keywords and phrases show a strong indication of potential sales opportunities as well as situations such as cancellation of orders. Speech analytics determines the needs of a customer by the use of keyword detection whereas voice analytics, saves time and labor by guessing the meaning of words and phrases used in a conversation.

Furthermore, by analyzing a customer’s response and emotional state, voice analytics can help predict future behaviors. This is used in second call targeting by focusing on customers likely to make similar purchases. Thus, differentiating between what has been said with respect to how it was said can provide with different kinds of information, that may be used to improve the quality of operations in various ways.