Jul

nmodes Technology - Overview

                                                       

nmodes ability to accurately deliver relevant messages and conversations to businesses is based on its ability to understand these messages and conversations. Once a system understands a sentence or text, it can easily perform a necessary action, i.e. bring a sentence about buying a car to the car dealership, or a complaint about purchased furniture to the customer service department of the furniture company.

Understanding sentences is called semantics. nmodes has developed a strong semantic technology that stand out in a number of ways.

Here is how nmodes technology is different:

1. Low computational power. We don’t use methods and algorithms deployed by almost everyone else in this space. The algorithms we are using allow us to achieve high level of accuracy while significantly reducing the computational power. Most accurate semantic systems, e.g. Google’s, or IBM’s, rely on supercomputers. By comparison our computational requirements are modest to the extreme, yet we successfully compete with these powerhouses in terms accuracy and quality of results.

2. Private data sources. We work extensively with Twitter and other social networks, yet at the same time we process enterprise data.  Working with private data sources means system should know details specific only to this particular data source. For example, when if a system handles web self-service solution for online electronics store it learns the names, prices, and other details of all products available at this store.  

3. User driven solution. Our system learns from user’s input. Which makes it extremely flexible and as granular as needed. It supports both generic topics, for example car purchasing, and conversations concentrating on specific type of car, or a model.

Interested in reading more? Check out our other blogs:

Social Engagement and Sales Accelerate When Using Intent-Driven Data

nmodes delivers consumer intent from social web to businesses. In real-time.

 

That is, if your company is selling cars we will connect you with potential customers out there that express intent to buy a car.

 

nmodes has partnered with a medium-sized travel company to help grow their social web sales channel. Our approach is to deliver consumer intent relevant to the company (people planning vacations, going on trips, flying to various world destinations, etc) and develop engagement strategies maximizing the impact of this consumer information.  

 

Here are the results based on 4 months of data:

• The most efficient way to achieve short-term sales turned out to be individually targeted promo campaigns. For example, our travel partner created an attractive vacation destination package, and nmodes helped to spread the word on social media to those intended going on vacation.

 

A typical conversation start leading to promo offering. nmodes intent-based solution made it especially easy to target only relevant end users:

• The response rate varies geographically.

Canada - 20%

USA - 64%.

• The conversion rate is consistent across all locations and is slightly above 4%. When concentrating on vacation packages we were targeting 20-50 prospects daily, resulting in 2-4 sales per week, averaged $15,000 /mo or $200,000 /year.

• The potential for this particular market segment (all-inclusive vacations) in the US is at least x10 higher.

• The engagement was based on the combination of intent-based data and location data.

An intent-based sample for European destination package, travelers from USA:

 

While working with companies from various verticals we proved that intent-based data paired with location data offers a powerful opportunity to drive sales aggressively and accelerate business growth.

 

nmodes is best equipped to ensure that your business can benefit from this newly available power.

 

READ MORE

Beware the lure of crowdsourced data

Crowdsourced data can often be inconsistent, messy or downright wrong 

We all like something for nothing, that’s why open source software is so popular. (It’s also why the Pirate  Bay exists). But sometimes things that seem too good to be true are just that. 

Repustate is in the text analytics game which means we needs lots and lots of data to model certain  characteristics of written text. We need common words, grammar constructs, human-annotated corpora  of text etc. to make our various language models work as quickly and as well as they do. 

We recently embarked on the next phase of our text analytics adventure: semantic analysis. Semantic  analysis the process of taking arbitrary text and assigning meaning to the individual, relevant components.  For example, being able to identify “apple” as a fruit in the sentence “I went apple picking yesterday” but to  identify “Apple’ the company when saying “I can’t wait for the new Apple product announcement” (note:  even though I used title case for the latter example, casing should not matter)

READ MORE