Tips to optimize your holiday text marketing strategies

The holiday season is here and research shows that consumers are ready to spend more to fulfill their needs during this period. As a retailer in the market, how would you cut through the bulk of promotions, offers, and clutter that consumers are going through?

SMS Marketing is the perfect way to reach out to your customers, once you have an opt-in list that you can send SMS messages. You can optimize our SMS campaign using the following tips.

Grow your SMS List:

Before you can use SMS Marketing, have a list of people who would like to receive messages. If you have a physical location foot traffic and walk-in are high during this period, you can offer your customers to  sign up for your list.

This time of the year you can grow your list faster than ever because of al the people that are constantly shopping.

Option to Reply:

All though many businesses are using SMS marketing to promote their offers, almost more than 95% of customers like to reply to the SMS and know more information and place the order instantly using SMS. mastered this by providing industry best SMS marketing solutions which can generate orders, give more information to customers using two way messaging unlike traditional one way SMS messages.

Time-limited Sales:

You can bump up your sales this holiday season by making your consumers take their shopping decision by creating flash sales and last-minute deals.

You can utilize SMS to notify your customers about these sales, as the delivery time in SMS is almost instant and fast.

Unlimited targeting rules:

SMS is not just limited to text messages, but with the advantage of short links, you can include images, videos, pdf, directions, and links to a web address. 

Stock alerts:

Notify your customers when your bestsellers go low on stock and create a sense of urgency or when new stock arrives in your store.

Interested to know more about how SMS Marketing & Customer Engagement can help your business during this holiday season.

We are also partnered with intuit QuickBooks, Clover POS, Yext to create a great experience 

Sign in with intuit :

Install on Clover :

Install on Yext :https:

with Google:


Have more questions or need assistance with your business, contact us at 

How can you build a constantly learning Virtual Assistant using Graph and Search techniques

Can you use the human in the loop to constantly improve the capabilities of the virtual agent?

Let us say you are developing a virtual assistant to handle customer service calls on Telphone for Hotel Chain. Your virtual assistant had to back out and take the help of a human to resolve the customer issue.

The virtual assistant can listen to the recording of the conversation between the customer service representative and the customer, converts the conversation to text using speech to text recognition techniques and analyzes the conversation for future use. 

The stored conversations/dialog are used to improve the intelligence of the software system on a continuous basis by storing the conversations in a graph data structure on an inverted index for efficient future retrieval. 

A dialog can be defined as the smallest element of the customer and business interaction. The system can build a bipartite graph with a hierarchy of dialogues. A dialog itself can be represented by two nodes and an edge between them. The dialogs are connected and branched off as new combinations rise for the business interactions across different communication platforms. The graph can be built on an inverted index data structure to support efficient text search. 

Elaborating further, to start with the opening sentence from customer service representative such as “Hello {Customer Name}! This is {Company}. How can I help you” will be represented as the root node of the graph. We note that the data in the node will have placeholders for the customer name, the business name. The placeholders in the conversation for building the graph are identified by looking for fuzzy string matches from the input dictionary consisting of inputs such as the business name, the customer name, the items served by the business, etc. The node is annotated with information about who the speaker (customer or customer service representative) was. The node will also have features such as semantic mappings of the sentence, vector computed using sentence2vec algorithm by training a convolutional neural network on the domain that the software agent is trained for. 

A different semantic response from the customer is created as a child node for the question from the customer representative. The semantic equivalence to the existing nodes on the graph can be done using learn to rank algorithms such as Lambda Mart borrowed from the search techniques after doing a first pass inexpensive ranking on the inverted index of the graph of conversation. In an implementation, the result with the highest score with Learning to Rank algorithm exceeding a certain threshold is used as a representative for the customer input. The semantic equivalence comparison and scoring is done after tokenizing, stemming, normalizing and parametrizing (recognizing placeholders) input query. Slot filling algorithms are used to parametrize the customer responses. The slot filling algorithms can use HMM/CRF models to identify part of speech tags associated with the keywords and statistical methods to identify the relationships between the words. If there is a match to an existing dialog from the customer, then the software system will store the dialog context and not create a new node. In there is not a match, than a new node is added to the node of the last conversation. 

Some tasks are simple question and answers such as “User: What is your speciality? Customer Service Representative: Our specialty is Spicy Chicken Pad Kee Mow ”. These tasks can be indexed on the graph as orphan parent-child relationships in the graph. 

One of the challenges we run into when we are building the graph to constantly learn is the change in context. If there is no change in the context, we create the node as a child of the previous node. If there is a change in the context, we need to start a new node different from the previous state in the graph. To figure out a change in the context when the customer talks to the customer service representative, we can use a Bayesian or SVM Machine Learning classifier. The classifier can be trained on crowdsourced training data using features such as the number of tokens common to current and the previous task, the matching score percentage between what the customer has said and the maximum score match of an existing dialog. To improve the accuracy of the classifier, we can train a different classifier for each domain. 

It is to be noted that the graph can be constructed manually by an interaction designer, which can then be inserted in an inverted index. In yet another implementation, a Recurrent Neural Network can be trained on the interaction between the customer and the customer service representative, if we have a lot of training data. To implement personalization to models in a recurrent neural network, user profiles can be clustered into several macro groups. We can use an unsupervised clustering algorithm such as K-Means clustering to accomplish this or create manually curated clusters based on information about the user such as age group, location, and gender of the customer. We can then boost the weight of the examples which had a positive conversion from the customer service representatives. In an implementation, this can be done by duplicating the positive inputs in the training data. The positive inputs can be characterized by things such as the order price and satisfaction from the customer. It is to be noted that the idea of personalization in neural networks is not specific to conversational customer interactions and can be used in things such as building model which send an automatic response to emails. 

The graph on the inverted index is then used to answer questions about the business by a software agent. The software agent starts from the root node of the graph and greets the customer on a call, SMS and Facebook Messenger. The customer can respond to the greeting with a question about the business by searching for the closest match to the question from the customer using techniques borrowed from information retrieval. In an implementation, this can be done using an inverted index to look up possible matches for the user input using an in-expensive algorithm to start with and then evaluating the matches with an expensive algorithm such as Gradient Boosted Decision Tree. Before hitting the inverted index, we have to run stemming, tokenization and normalization algorithm on the input query to make sure that the input can be searched properly by the algorithms looking for a match.

This was an idea I wrote in 2016, in a patent application for Vocy.AI (If you ever plan to use this technique for your company, please consider paying royalty to a poor innovator). Components such as Sentence2Vec can be replaced now with BERT and RNN can be augmented further with attention techniques.This approach gives control as well as the evolution of the virtual agent to enterprises.

with Google:

with Intuit:

Install on Clover App Market:

Install on Yext App Market :http://Install on Yext App Market:


Voicy.AI proudly partners with Yext to empower local businesses.

Today is proud to announce the partnership with Yext that will further assist the network of business clients to succeed in their Advertising, Marketing, Customer Loyalty & Customer Service. Taking advantage of Voicy.AI, business owners can save a lot of time and money.

Our user-friendly application SMS Marketing & Customer Engagement will help businesses to run SMS Campaigns to advertise and educate their customers about offers, promotions, etc. Our app gives businesses a powerful new tool to help them reach their customers in a targeted way.

Features like Quick-Replies will automate and handle complex customer service queries which for the most part involve the burden of a heavy time/monetary investment. Clients can access the Menu items in your Yext account and directly place an order with just a click of SMS. The ease of use in the app provides in combination with great results for any budget, it is the perfect pairing for any businesses looking for more leads and loyalty. 

The SMS Marketing & Customer Engagement can easily outperform any service provider at the lowest possible cost. Using advanced Artificial intelligence and Machine Learning techniques, It can efficiently improve advertising, client support needs. It is suitable for businesses of all sizes.

As a major player, we are positioned as a pioneer in the virtual agent space. We are also available with other partners, including Intuit QuickBooks, Clover POS, and other progressing partnerships to make this accessible to businesses of all shapes and sizes.

Install on Yext App Market:

with Google:

with Intuit:

Install on Clover App Market:



Engage with your customers using Conversational Text Messaging

Conversational marketing is a famous concept used by many companies to narrow down or reduce their sales cycle and create a more interactive experience to their customers while buying.

Unlike traditional marketing, conversational marketing utilizes the chatbot technology to create a more natural and human experience to the customer. They can gather information any time, instantaneously without  delay in the response time.

Using Conversational SMS you are not just reaching out to people only asking them to make purchases but also answering their questions and providing more information about your business.

Customers are cluttered with various different companies and offerings for exactly the same product. The buying experience has changed and people want to make sure they have more information before they make a decision. Using conversational SMS customers have more information about the company and their products.

SMS Marketing & Customer Engagement application by Voicy.AI has mastered the conversational marketing space by providing marketers the freedom to not just to run SMS Campaigns but also create interactions between the business and customer. The unique application has pre-built flows which can generate orders and also customizable for the various needs of marketers.

Using conversational SMS is very simple, just ask the customers to reply with an associated keyword, number, etc. Once they reply the response is sent instantly.

Conversational text messaging can save time by automating your customer service and engage your customers with relevant and professional conversations all the time.

Start engaging with your customers now by using Voicy.AI’s SMS Marketing & Customer Engagement app.

with Google:

with Intuit:

Install on Clover App Market:


Have more questions or need assistance with your business, contact us at



How SMS Marketing can impact your business

Regardless of the span of the business everybody began incorporating SMS Marketing in their marketing blend.

Numerous organizations are utilizing SMS as an approach to connect with their customers when they are most likely to stop by your business.

If you have not considered it yet, it is the time to reach out to all your customers. More than 2.5 Billion people have smartphones that are capable of text messaging.

Latest statistics state that people tend to receive communication over a text message over any other source like talking over the phone, email, etc.

Voicy.AI has developed a perfect solution for all your SMS needs using SMS Marketing & Customer Engagement application.

Features & Advantages of SMS Marketing & Customer Engagement:

  1. Reach out to all your customers within seconds using Voicy.AI’s SMS Marketing & Customer Engagement App.
  1. Interact more with your customers and allow them to respond back to your messages quickly and easily.
  1. Give information about your products and service and generate orders all by using SMS
  1. Taking advantage of Conversational Marketing, make your customer engagement mechanized with pre-constructed SMS streams and adaptable Quick Replies
  1. Text messaging almost provides results almost instantaneously.
  1. People tend to open their text messages with a few seconds or minutes.


If you are not using text messaging as one of your marketing strategies, start using SMS Marketing & Customer Engagement and accelerate your brand loyalty and awareness. Voicy.AI offers SMS Marketing and Customer Engagement application beginning from 9.99$ per month.

with Google:

with Intuit:

Install on Clover App Market:

Standout this Black Friday using Conversational SMS Marketing

Black Friday is the day following to Thanksgiving and it has been the busiest shopping day since years in the United States. And Cyber Monday is celebrated on monday next to Thanksgiving. It is created in recent years to cater to the emerging online shopping experience.

It is the time of the year where everything is on sale and shoppers rush out to stores to clear their wishlists.

Marketing is a huge clutter during this time and people see offers and promotions all around and the email inbox is filled with promotional emails. Marketers struggle all their ways to ensure that people are aware of the offers and discounts offered by them.

Here is how you can make shoppers notice and take action using conversational SMS from Voicy.AI

SMS Marketing is one of the fastest and most effective ways of communicating with an open rate of more than 96%. People are always with their mobile devices and most of them tend to notice their message notifications within a few minutes.

Voicy.AI has perfected the SMS Marketing solution by making the SMS conversational and providing the option to customize the SMS Chatbot.

Now customers can not only know about the promotion but also place an order directly with a simple reply by taking advantage of the unique order generation feature. Not just that, Customer service is being taken care off by providing information to the customers like timings of the store, location and all other general questions answered instantly.

You can alert all your customers during this Black Friday and keep them loyal by providing them with exclusive coupons, shopping links and much more.

Start using SMS Marketing & Customer Engagement by Voicy.AI for your Black Friday promotions and standout in the clutter of deals and promotions.

Sign in with Intuit QuickBooks

Install now on Clover App Market

Sign in with Google



Method to generate Natural Language

Generating Natural Language from few seed sentences without human for an intent has been a challenging problem in Chatbot industry. Here is my proposal:

a) Apply a sequence to sequence model with attention on filtered SemEval dataset.

b) Loop through each seed sentence and generate a semantically equivalent sequence to sequence model from step a.

c) Take generated sentences from step b and add it as a seed sentence and recursively apply step b till you get sentences which are not semantically similar as evaluated by say a Siamese Network.

What are your thoughts? Can you please let me know the results, if anyone gets a chance to implement it?

Improve your sales this Halloween with these simple marketing tips

One of my customers visited the salon soon after Halloween last year and said “Hey, thanks for getting that perfect spooky look on my face last night. My colleagues were all surprised at the Halloween party we had and were enquiring about your saloon. One of them got so fantasized with the nail art you made. Well done!!”.

She asked if I have any monthly packages so that it will be pocket-friendly for her to visit my saloon. Well, I had no packages or promotions in my mind by that time, but gave 30% off on the total price of all the services she was looking for. She was so happy and said “I guess it’s just that your saloon isn’t at the right location, but you have some incredible talent. Why don’t you try promoting your salon and services seriously? Actually, I can help you out with this.”

She sat down with me and jotted these five ideas that will work well in promoting my salon. I started implementing these salon marketing ideas for every festival season and they earned me some whooping profits. I am going to use these extensively even for this Halloween and thought of sharing with others who want to promote their small-time salons.

1.Halloween face painting or nail art: One way to showcase your clients what your skills are is to offer free face paint or nail art service to all kids who go for Trick-or-treating in your town. Promote that parents can come in for any service at your salon and you will face painting for their kids for trick-or-treating. Run this throughout the month and give out the coupons for face painting or nail art that can be redeemed a day before or on the day of Halloween.

2.Organize a social media contest: You can organize a social media contest (for eg: #hashtag contest), with some interesting theme. Host this event for a day or two at your salon and you will get a good list of the customer base to promote your services. Don’t forget to decorate your salon in Halloween or any other theme and concentrate on your perfect look that matches the theme you chose. Plan this at least 15 days before Halloween.

3.SMS Marketing: Now that you have developed a base for your promotions, add some Halloween texture to your messages and spread them across that base. Marketing SMS is the easiest, fastest and cheapest way to spread the fire of your offer. I chose Voicy.AI as marketing SMS solution to spread the word and manage the responses and bookings. They made my life easy all throughout the season by their SMS marketing service. Unlike other SMS providers, Voicy.AI offers Two – Way SMS Marketing and their Quick Replies feature lets you automate your customer service needs and make unlimited customization to their SMS chatbot.

4.Group Vouchers exclusive for Halloween: You can distribute vouchers at cafeterias or small businesses, which offer a handful of services with attractive discounts to a group of 4 or 5 people.

5.Gift them when they visit you: Who on the earth doesn’t like to be treated well or gifted? Keep some gifts to give your customers when they visit your place. Make them customized with your Salon details in some corner (careful about this, you give them to use them) or buy some yummy treats. Keep some surprise vouchers, which makes them visit your place again.

In the age of electronics and internet, make wiser choices to reach out to your target audience. I made a wise choice by reaching out to the right people via Voicy. The best part is, it could handle the responses and queries for bookings amazingly well and generate orders with its intellectual system. That’s how I increased my salon’s visibility through technology, more than by its geography.

How Facebook can trump Google in advertising

A major percent of internet advertising revenues are shared by Facebook and Google. Facebook makes it advertising money using re-targeting, and latent targeting on user profiles. Google uses an auction model built on search queries to fill its coffers. Search query is one of the top most actionable intents from the user on internet. Google has built an amazing business around it.

Facebook has got more or less monopoly around social communication. Social tweets and messages don’t have a merchandising intent, similar to search queries. Facebook has trickily used the re-targeting mechanism (Disclaimer: I patented the idea, before anyone has implemented it) to make the ads more actionable.

We will eventually be at a stage, where Facebook and Google will be fighting for the same ad dollars. Who has got a strategic advantage to win the war? In my view it will be Facebook.

Elaborating more, Facebook controls the user’s interests and influences across its social properties. Facebook can use the personal data from the users to predict search queries and information that the user will “Google” in the near future and make it as part of the user stream. You might ask, is it possible?

How can Facebook predict search queries before they happen? Facebook has got a search engine on its page and has got a partnership with Microsoft’s Bing. They have access to both what the user is doing at any given point of time, what their influences are and what their search queries will be through its popular properties and partners. They also have significant information on a user through their re-targeting program, about their activities outside of the social walls.

Using above data, one can use variations of Sequence to Sequence algorithms to give search queries. The input sequence can be the aggregated behavior. We can use social profile embeddings, image embeddings in the social stream, previous search queries, the location information as inputs for the Sequence to Sequence algorithm. We can us a Variational encoder for representing the input data. The output sequence can be a list of search queries that the user will type on Google. One can also pose the query prediction as a recommendation problem. We can train a wide and deep neural net on the user’s data and search queries to predict search queries. We can also borrow techniques from Zero Query search engine techniques to do the predictions and generate information in Social Streams, so that users don’t have to go to Google to get information.

It would be a great win for users and Facebook, if they can stop the interruption on social browsing by 50%. Facebook can make money by asking the advertisers to bid on predicted search queries. It might be an easy sell, to the advertisers, with their relationships and engagement numbers.

If I were Google, I would be really scared of this possibility and eventuality (Most probably in the next two years). I would break the Facebook’s monopoly on communication as early as possible.

Disclaimer: My friends at Facebook and other social networks, if you decide to implement this idea, I would appreciate, if you can pay me royalty for the patent I filed with title “Advanced techniques to improve content presentation experiences for Businesses and Users”. Please don’t ignore legal notices from a poor innovator :).

Visit us at for more information.

Google Duplex technology solution for your business

Were you amused by demo of Google Assistant calling a business? The demo fused the elements from Speech Recognition, Natural Language Understanding, Natural Language Generation and Text to Speech and was nicely presented by Google’s team.

We at Voicy.AI has been perfecting Google Duplex like technology for businesses from 2015 building upon our customer engagement patents from 2010. Specifically, our patent with title “Systems and methods for virtual agents to help customers and businesses” talks about several ideas that were shown in Google’s demo. We also talk about several next generation customer engagement solutions and conversational commerce ideas in the patent. It is a great sense of personal satisfaction and pride to know that our team has recognized the opportunity before the industry leaders and great teams at Google, Facebook and Amazon.

In addition to patents, we also pioneered one click virtual assistants for businesses on Telephone using our technology. We converted a complex implementation consisting of Telephony platform, Speech to Text, Dialog Engine technology and custom implementation typically costing millions of dollars from bigger companies to a simple one click SAS solution.

You can subscribe to our AI Telephone assistant solution and reduce your customer services costs from thousands to hundreds of dollars and provide 24/7 service to your customers. You not only get our technology, but also get coverage from our patents. Please reach out to, to see how we can help your business.