Guavus: Helping CSPs Drive More Value from Their Data Using AI-driven Analytics

Guavus

Guavus (a Thales company) has been built from the ground up with a singular focus – serving communications service providers (CSPs). The company enables its CSP customers to do more with less: drive more value from their data, at a lower cost.

With more than a decade of experience in streaming data analytics for CSPs, Guavus understands the needs of CSPs and their highly complex networks which process huge volumes of data every day. The company has consistently met these needs with carrier-grade solutions that deliver definitive success and reliability.

Guavus’ commitment to the CSP market has led to a resilient and extensible product portfolio that easily integrates into mobile network operator (MNO) and mobile system operator (MSO) network architectures. The company’s real-time streaming data collection is highly available with local redundancy and has the ability to replay data in the event of system failures. The flexi-binning methodology utilized allows Guavus’ solutions to intelligently and automatically handle data delays or mismatched speeds when aggregating data from multiple sites without any manual intervention. This is an important part of why the company can handle the scale and performance required in CSP networks, which are often massive and complex.

 

Abiding by the ‘Analyze First, Store Later’ Principle

Guavus was founded in 2006 with the sole mission to provide real-time streaming analytics for CSPs. In 2017, the company was acquired by Thales and is now a part of the Digital Identity and Security global business unit. Guavus has locations in the United States, Canada, India, Singapore, and Australia, and caters to a global customer base of MNO and MSO customers.

Historically, Thales has been involved in the aerospace, defense, transportation, and related industries. However, in 2016, it started acquiring software companies, with the aim of supporting its own digital transformation and to enable its clients’ transformations. In particular, it has focused on the following areas: security, artificial intelligence (AI), and real-time advanced analytics. From a technical perspective, Guavus offers AI-based analytics at the network edge and in the core of the network for central processing, which can be deployed on-premise or in the cloud.

Unlike some other data science-oriented analytics providers, Guavus has, since its inception, been very focused on providing CSP solutions rather than generic products. Currently, these include operational intelligence, security intelligence, marketing intelligence, and smart industry and IoT solutions among many other use cases.

The founding principle of the company was based on an ‘Analyze First, Store Later’ model as opposed to the traditional paradigm of centralized store-first analytics which in actuality doesn’t work for large-scale, distributed, real-time analytics. It’s key is to analyze the data as it comes in and, once people can do that, they can start pushing out timely decisioning applications for real-time insights and support.

 

AI-driven Predictive and Prescriptive Analytics for Improved CX and Lower Opex

Anukool Lakhina is the Founder of Guavus. While doing his Ph. D project at Sprint Advanced Technology Labs, Anukool realized the importance of analyzing data in a timely manner. “The lab had a really audacious idea, some would even call it crazy. The idea was this: what if we could collect every single packet from our network?” recalls Anukool. “Back then, we only had enough storage to collect data for an hour. So, we would turn on the sensors and after collecting an hour’s worth of data we would fill up all the drives and turn the sensor off.”

At that time, it was much cheaper and faster to physically ship the data to a central lab via FedEx versus the backhaul network. Once the data had arrived, the labs would run an analysis that would effectively reveal many interesting insights about customer demands on the network, security threats, etc. Though this was seen as interesting, such insights were of limited value to the business and operational teams as most of them were latent and only seen in hindsight. This feedback led to the genesis of Guavus, a real-time big data analytics firm based in San Jose, California. Since its inception, the company’s sole purpose has been to solve the problem of enabling real-time decisions with massive volumes of data.

The original idea of Guavus was born and the purpose was to instrument the networks in such a way that enables the collection of all the data from the associated CSP networks efficiently. “This was before there were phrases like big data, AI and data science,” recalls Anukool.

The emergence of AI has allowed the company to go beyond statistical analytics to arrive at accurate conclusions and predictions. This goes beyond recognizing patterns to machine reasoning, thus putting data into context and enabling the network to predict and prescribe actions. By leveraging machine learning (ML) and AI, CSPs can predict the needs of their customers and their systems, automate preventative actions, enable more comprehensive customer care, and create personalized offers based on subscriber behavior and interest.

 

Serving Clients with Powerful AI/ML Accelerators

Guavus has a long history of working with the top service providers worldwide – analyzing their huge volumes of high-velocity data and enabling actionable insights through the analytics it performs. The company’s suite of products is powered by a rich AI-driven behavioral analytics engine running behind the scenes. Pre-built advanced ML algorithms packaged as “accelerators” are applied on hundreds of terabytes of real-time streaming events to solve a wide range of use cases across network operations, marketing, customer care, experience management, security, IoT and subscriber-based monetization.

These actionable insights allow Guavus customers to integrate their orchestration systems to enable true close-loop automation of their processes. The company has solved use cases ranging from diagnostic to predictive and prescriptive analytics which assists its customers in their daily workflows without the need for advanced analytical training.

For example, the AI/ML accelerators powering Guavus products address problems such as incident prediction, anomaly detection, behavioral analysis, root cause analysis, ensemble classification, concept extraction, risk bucketing, sessionization, continuous learning, and reasoning.

 

Exploring New Ways to Apply AI/ML Analytics 

Anukool believes AI and ML are shaping the landscape with their capability to provide innovative solutions to some long-standing problems. They are enabling new ways of problem-solving and automation capabilities, whose impact is manifested in every software interaction in our day-to-day lives – from healthcare to finance, from education to social media, from shopping to online gaming.

Guavus has realized the disruptive potential of AI/ML and the powerful impact it has for CSPs and their customers across industries. One of the many success stories is in the field of customer service where reducing the mean-time-to-diagnose (MTTD) and mean-time-to-resolve (MTTR) network issues have a positive impact on customers’ experience. This is emerging as a big area of success for AI across many different industries. In addition, the company’s products offer AI/ML-powered decisioning in optimized network operations, IoT connectivity services, connected vehicles, fraud detection, dynamic pricing, customer personalization, asset management among many other applications.

AI/ML can help CSP networks become self-optimizing and even self-healing. Behavioral techniques are used to analyze normal and abnormal behavior and predict fraud. Natural Language Processing (NLP) is heavily used to parse large amounts of training and support material to create an accessible knowledge base that can be used by operators to resolve issues quickly. The cost savings along with the competitive advantage offered by these solutions are huge incentives for Guavus’ customers to be interested in these innovative solutions.

 

Industry-leading Solutions Driven by Experience with Top CSPs

Anukool says that the company’s experience with the top CSPs has driven its architecture and design of its products to handle the scale and data quality needs of the most demanding environments – processing petabytes of data at high speeds, each day. Guavus created stream processing software before Spark was invented and has years of expertise in this software capability. The company focuses not only on the stream processing of data but also on the curation of the data in real-time. All of this is done while making the data highly available and suited to meet the end application’s need.

 

Remarkable Success with CSPs and Industry Accolades

The world’s largest CSPs rely on Guavus to increase efficiencies, create new revenue streams, and improve their customers’ experience. The company’s deployments span the globe with installations in Europe, Asia, and Africa. Guavus is driving digital transformation at all of the Tier 1 MSOs and at 6 of the 7 world’s largest telecommunications providers.

Moreover, the company’s customers are able to analyze big data in real-time and take decisive actions to lower costs, increase efficiencies and dramatically improve the end-to-end customer experience – all with the scale and security required by next-gen 5G and IoT networks.

The top 4 MSOs in North America and Europe use Guavus’ operational analytics solutions to unify siloed data, optimize operations, and reduce time to resolve issues. The company’s earliest technology was focused on the collection of data at extremely high data rates from locations across large geographies.

Guavus has won many industry awards and accolades throughout the years. Some of these include:

•  Data Breakthrough Award – Cross Infrastructure Data Analytics Solution of the Year (2020)

•  Frost & Sullivan Award – Global Smart Data Analytics Enabling Technology Leadership (2019)

•  Insights Success – The 10 Most Disruptive AI Solution Providers (2019)

•  Analytics Insight – The 10 Most Innovative AI & Cognitive Solution Providers (2019)

•  insideBigData Impact 50 – The Industry’s Most Impactful Companies in Big Data (Q2 2019)

•  Global Telecoms Awards – Advancing Artificial Intelligence finalist (2019)

•  The AIconics Awards – Best AI Application in Customer Service finalist (2019)

•  Frost & Sullivan Award – Global Big Data Analytics Customer Value Leadership (2018)

•  CIOReview – 20 Most Promising Big Data Solution Providers (2018)

•  The CEO Views – Top 10 Most Admired AI-Solution Providers (2018)

•  The Silicon Review – 50 Most Innovative Companies to Watch (2018)

However, the highest award that the company has received has been its customers’ business. “It is an honor to serve the CSP community and to be installed at leading service providers throughout the world,” says Anukool.

 

The Future Roadmap

Guavus is focused on business value problems it can solve for its CSP customers and how it can leverage AI and ML for that purpose. The company is driven by the current problems seen by CSPs such as achieving higher levels of subscriber satisfaction, reducing subscriber churn, and improving the availability/quality of services on the mobile network.

Anukool believes the mobile network will continue to change and evolve as new services demand higher levels of security, performance, and scale. Requirements will evolve over the next 2-3 years, with the advent of 5G, which will increase the need for greater automation, control, and insight as CSPs are seeing ways to enable the network to achieve its own optimization and maintenance. It’s Guavus’ belief and the prediction that AI and advanced analytics will be critical in achieving this vision and that it will need to be deeply embedded in their operational DNA.

No Comments so far

Jump into a conversation

No Comments Yet!

You can be the one to start a conversation.

Your data will be safe!Your e-mail address will not be published. Also other data will not be shared with third person.