ARCHIVE FOR THE ‘machine-learning’ CATEGORY

In the latest Field Service Podcast, Paul Joesbury, Commercial Operations Director at Homeserve, suggests the asset will eventually become more important than the engineer in service.

 

In this special episode, Field Service News' Deputy Editor Mark Glover, speaks to Paul Joesbury ahead of his debate at Field Service Connect next month where he will argue that the use of technology such as machine learning and AI will eventually negate the need for the human intervention.

You can find out more information about Field Service Connect which takes place on 15 and 16 May at Celtic Manor, South Wales here. 

Chris Ruff is the President and CEO of location-based technology outfit Glympse and was a recent a guest on The Field Service podcast. Here Deputy Editor Mark Glover cherry-picks some highlights from the interview including automotive technology, machine learning and a misty-eyed look at the hardware that inspired him.


Let’s travel back to 1999, the year of the Palm VII, seen as the first truly wireless handheld device. Chris was (and still is) a fan. “It was why I got into wireless,” he says with nostalgia. “The idea that we run little applications on mobile devices was hugely inspiring to me. It was amazing because, until that moment, most of our experiences were from a dial-up modem in hour homes and we’d sit in front of our PCs, and that was how we got content and communicated with people.

“Now all of a sudden with this mobile device we were able to view content and share things with people. It really became the beginning of mobility and mobile applications. Starbucks had an app where you could find stores. It was really amazing, you could find coffee on your Palm VII.”

Is it collecting dust in Chris’ loft? “I might have it in a box somewhere,” he says laughing. “I tend to keep all my devices. I know I have seven generations of BlackBerries up there. They soon became my addiction."

“Mobile device improvements have been modest ones,” he says when I ask him about the evolution of mobility hardware. “They are mostly around cameras and screens but the underlying tech has been pretty stagnant for several years and generations now. It means it’s becoming a pretty mature market, just like the PC,” he suggested.

Chris has been with Glympse just over a year now, prior, he spent a significant chunk of time – 18 years – at connected car technology and automotive telematics provider Xevo where he joined in its infancy, overseeing various executive positions and becoming its President, CEO and Chairman. He remains on the board.

"Starbucks had an app where you could find stores. It was amazing, you could find coffee on your Palm VII...” 

The potential of automotive technology, therefore, forms a good part of our conversation, most notably when I ask where he sees the next big disruption in field service. “I believe that in the big Iot space that autonomous driving will create a huge change in field service,” he says. “It’s going to make everything more productive, it will improve communications with consumers and it’s going to make it safer. I think this will re-shape the industry more than any tech enhancement than we have today.

He also cites machine learning as a significant enabler in the sector, providing service in real-time and pre-empting faults but he thinks another pinch point could be the way a product is delivered, syncing with the arrival of the technician.

“We’re currently looking at way of tracking two or more things simultaneously, in a healthcare scenario, for example,” he explains. “Here a skilled nurse and the drugs they need to administer need to be at the patient’s house at the same time.

“You could see that in some of the advanced field services and even big machinery cases; where the part and tech show up at the same time, assisted by machine learning that alerts the service company when the asset is about to break.”

I ended the podcast by asking what motivates Chris in his work. His answer is wide-ranging that touches on potential of technology as well as making a difference in society. “I’m motivated by two things,” he says. One is being able to continually push the envelope of what’s available using technology. Two is making a difference in the world.

Can he cite an example? “During the hurricane season, while the search and rescue operations were taking place, teams were using Glympse to keep track of each other, ensuring they wouldn’t lose touch while they carried out the task.

“That to me is super inspiring. That I can work on technology that actually makes a difference in people’s lives.”

Digital Transformation is currently one of the key trends amongst field service organisations in all industry verticals, but it is a revolution that has been building for a long, long time writes Laurent Othacéhé, CEO, Cognito iQ. 

Field service is undergoing what is in my opinion the biggest change the industry has seen in the last 25 years.

All of our customers, across a range of industries, want to talk to us about Digital Transformation, and how they can use digital technology to fundamentally transform the way they interact with their customers, and not just about the operational ‘nuts and bolts’ of delivering a service to them.

Some customers are only at the beginning, taking small steps towards transformation by, for example, moving away from traditional software ownership models towards cloud-based products and services, such as MS Office 365. Others are further along, with strategies that embrace technologies such as IoT, big data and AI.

But regardless of their progress, at the heart of all of these conversations is the recognition that Digital Transformation will bring them closer to the goal of providing exceptional field service.

The Art Of Field Service Ops
I often think that the role of a Field Service Manager is a complex mix of art and science, with a bit of magic thrown in for good luck.

Decision making needs to adjust constantly to changes in conditions – a sudden unseasonable cold snap, for example, or a contract with a new customer. Just as service delivery metrics point to success, something changes, and there is a whole new dynamic.

Without knowing what combination of factors triggered the change, it’s hard to know how best to respond.
Get the reaction to an emerging threat wrong – too great or too small a response – and the complex balance of the operational ‘ecosystem’ can be thrown out.

Recovering that balance and restoring the conditions required for ‘flawless’ field service can prove costly and time consuming.

Data doesn’t drive decisions
Most organisations capture a range of sources and types of data - workload planning, resource availability, schedule efficiency, service outcomes, customer satisfaction levels, asset profitability – and many are integrating new types, such as that offered by IoT.

However, this data is rarely delivered in the right form to support decision making, meaning that managers spend too much time aligning and manipulating data from disparate sources. Even then, many are frustrated to find that the root cause of issues is still unclear and the likely outcome of any decision is still uncertain.

AI, machine learning and predictive analytics
This is where the latest technologies, such as AI, machine learning and predictive analytics come in.

Valuable insights into the performance of an operation often lie at the intersections of these various datasets; these technologies can enable decision support applications to identify underlying patterns of performance in the Field Service operation, including long and short term trends, that were simply too complex for traditional applications to uncover. This is increasingly true as much larger data sets such as IoT have come online in recent years.

"Field service is undergoing what is in my opinion the biggest change the industry has seen in the last 25 years..."

This deep understanding of performance, combined with the power to highlight exceptions in real-time, enables the operations team to see the correct course of action to address each challenge as it arises. And beyond simple advice, these technologies make it possible for applications to automate ‘learned’ responses to common patterns of exceptions that occur.

The next generation of decision support
This next generation of applications will be used strategically to analyse, for example, which factors within a field service operation make engineers productive, and which inhibit productivity. Some of these factors will be within the control of the engineer, in which case performance can be addressed with initiatives such as better training or incentives.

Others will relate to company processes, in which case the applications will suggest tactical improvements, the impact of which can also be measured. Others still will be external factors which can’t be changed, but can be allowed for in planning and scheduling.

Such applications will be programmed with a knowledge base, but will be learning all the time, as the outcome of each decision is fed back into the performance data, effectively automating the process of continuous incremental improvement. This will take some of the challenge of blending art and science out of the hands of the Field Service Manager, leaving them free to concentrate on other activities.

Not just software suppliers
It is clear that this massive change in the industry requires those of us who supply and partner with field service companies to change too. We can’t just be technology suppliers.

We have to embrace our customers’ goals and work with them to add value; to weave their transformation strategies into the fabric of our products and services and to bring to the table our own blend of art, science and, yes, a little magic too.

Laurent Othacéhé is CEO at Cognito iQ.

In the the final article in our current series of articles from field service solution provider Astea focussing Artificial Intelligence and Machine Learning,  we see how applying the Machine Learning can lead to better service resolutions... 

---

Is Machine Learning a key topic for your organisation?!

There is a detailed white paper on this topic authored by Emily Hackman and Liron Marcus which is available to fieldservicenews.com subscribers within our premium content library... 

---

Sponsored by: 

 

 

---

Data usage note: By accessing this content you consent to the contact details submitted when you registered as a subscriber to fieldservicenews.com to be shared with the listed sponsor of this premium content who may contact you for legitimate business reasons to discuss the content of this content.   

---

 

Congratulations, if you have been following this series of articles across the last few weeks you are now a cognitive technology guru! (If you haven't don't fret! we've written a whole white paper on the topic which is available to fieldservicenews.com subscribers.)

In the series we've tried to give you an understanding of how and why the field service industry is applying these new technologies, and you see the writing on the wall: positive results for your customers, your employees and your financial success.

Now it’s time for you to go through the machine learning process yourself in order to answer the most important question ever asked in a field service scenario: “What is the best resolution to a given problem?”

If we break this question down into smaller operational components, we first need to maintain a set of wide range problems represented in groups which share similar characteristics. We then label these groups. Let's say, in our case, how the problems were fixed or repaired. Then, we need to create a learning process that labels a new problem based on its characteristics.

 

The Learning Process

 

 

 

 

---

The learning process requires “real world” raw data and actual business experts. In our example, this data will be historical incidents and service requests that could most likely be predictive. The business experts are the people with extensive knowledge of hands-on technical support and service (e.g. field service managers with years of service and product experience.)

The next step is called data preparation. This step is required to screen the raw data, remove duplicate or irrelevant records, handle missing data attributes, and extract indicators and features that are needed in the learning process.

"Free text", such as the problem description of these examples, is then extracted into a bag-of-words model. This is a representation of the description text with meaningful information (disregarding semantic relationships in the sentences).

The next step is called the training process. This is where the actual learning happens. Different types of learning algorithms are applied to a data training set (a subset of the entire data to learn from).

The learning process requires “real world” raw data and business experts. In our example, this data will be historical incidents and service requests that could most likely be predictive.

The choice of those metrics influences how the performance of the machine learning algorithms is measured and compared. Accuracy is one of the metrics to evaluate and classify models. It calculates the number of correct predictions made by our training model over all kinds of predictions being made. Another metric, called the confusion or error matrix, is a two dimensional table that visualizes “actual” versus “predicted” results for different questions, called the “classes”. It shows if a model is confusing two classes (e.g. commonly mislabeling one as another).

Aptly named, the confusion matrix visualizes “actual” versus “predicted” results for different questions, called the "classes". It shows if a model is confusing two classes.

 

 

---

Do you want to know more?!

There is a detailed white paper on this topic authored by Emily Hackman and Liron Marcus which is available to fieldservicenews.com subscribers within our premium content library... 

---

Sponsored by: 

 

 

---

Data usage note: By accessing this content you consent to the contact details submitted when you registered as a subscriber to fieldservicenews.com to be shared with the listed sponsor of this premium content who may contact you for legitimate business reasons to discuss the content of this content.   

---

 

In the third article in our current series of articles from field service solution provider Astea focussing on Artificial Intelligence and Machine Learning we now take a look at some of the practical applications...

---

Is Machine Learning a key topic for your organisation?!

There is a detailed white paper on this topic authored by Emily Hackman and Liron Marcus which is available to fieldservicenews.com subscribers within our premium content library... 

---

Sponsored by: 

 

 

---

Data usage note: By accessing this content you consent to the contact details submitted when you registered as a subscriber to fieldservicenews.com to be shared with the listed sponsor of this premium content who may contact you for legitimate business reasons to discuss the content of this content.   

---

 

Thanks to early adopters and industry analysts, you know that augmenting your service business with intelligent systems can be useful in enhancing organisational performance. Now let’s review four examples of how field service companies can apply these technologies in order to gain insight and improve performance.

 

1. Dynamic Scheduling

Dynamic scheduling provides optimised schedule and planning of field service agents. It’s constantly updating in response to events in real-time.For example, when a new high priority service ticket is received, it needs to be scheduled for immediate execution and all other tasks must be postponed.

There’s an element of AI in this process because the scheduling system must perform its task of scheduling this service order intelligently. In other words, it must think and thus deduce that simply prioritising this service ticket is not enough. All other tickets must be postponed in order to ensure that the high priority one is resolved first.

For example, let’s say a call has arrived in the system and agents Steve and Karen have the same skills and are both available. The system decides to assign Steve as the agent for the call by considering the nearest agent rule. However, by looking back at history and identifying patterns based on call attributes and agent performance, we find that while Steve is located closer to the customer site and is more experienced, Karen is the right agent to dispatched. 

Why? The pattern shows that Karen has a higher probability to resolve this call on the first visit as compared to Steve. This prediction can be done only if the scheduling system reviews historical data and learns from it. We can even find that having more experience and arriving earlier to the site doesn’t necessarily deliver better results.

 

2. Customer Contact Center

Call center agents play a key role in customer satisfaction. They are usually the front line of the customer’s experience, so it’s crucial to invest in systems that improve the way call centers are evaluated.

Two of the important indicators to assess the efficiency of call centers are “first call resolution” and “average time in queue”. Calls are typically analyzed manually by the agent who is listening to the call and determining the context. Agents also have access to a knowledge base to help them.

Unfortunately, having a human evaluating each call to determine the course of action is time-consuming and does not guarantee the best solution.

 

3. Service Contract Renewal

Service contracts are one of the most important parts that a field service organisation can ensure ongoing revenue from customers. However, these services are provided for a limited timeframe

only, after which customers have to renew their contract in order to continue receiving the services. It is very critical for the businesses to understand the underlying reasons that impact contract renewal. Traditional ways to evaluate the chance of renewal are based mostly on client satisfaction survey results. However, a lot of important information is captured as free text from emails, notes, problem descriptions, etc. while call center and field service agents interact with customers in trying to resolve service requests.

Using this unstructured textual information, with the aid of machine learning algorithms, we can perform a sentiment analysis to detect a customer’s emotions about the service or specific product. This allows companies to classify the root cause of problems that lead to a customer not renewing a contract.

Machine learning algorithms can perform a sentiment analysis to detect a customer’s emotions about the service or specific product. This allows companies to learn why a customer does not renew a contract.

 

EXAMPLE: “Your customer support is great, however battery only lasts for 30 minutes.”

When analyzing the sentiments in this sentence, we can classify that the cause that could potentially lead to contract non-renewal is not related to the service, but rather is based on the product itself. As a corrective action, we can propose an upgrade to a newer model in which the battery life has been significantly improved.

With sentiment analysis, companies can respond quicker to signals, track changes in customer sentiment over time, determine if particular customers feel more strongly about their services, and predict the likelihood of contract renewal.

4. Inventory Management

Efficient inventory management revolves around knowing your demands. On one hand, companies must ensure that they have enough stock in their warehouses to meet the ongoing demands. On the other hand, they must preserve a small quantity of slow-moving items. Traditional solutions rely on formulas to reach static sets between pessimistic and optimistic values, and because of that, the chosen buffer level does not guarantee that the stock level fully satisfies the demand.

The way in which data can be incorporated from different external sources, including non-business data, helps machine learning models to find a correlation between the different variable factors and to optimize stock levels dynamically.

For example, feeding weather conditions and inventory data into a machine learning model can identify that specific parts tend to fail when the temperature outside is above 90 degrees Fahrenheit. In case the weather forecast shows that a heat wave is approaching, several proactive actions can be initiated, like ordering a sufficient quantity of items that are likely to break down so that those items can be used for predictive maintenance visits. Essentially, the machine learning model predicts the necessary stock level and determines how much inventory to order by using the past records of weather and failures.

The machine learning model can predict the necessary stock level and determine how much inventory to order by using the past records of weather and failures.

 

---

Do you want to know more?!

There is a detailed white paper on this topic authored by Emily Hackman and Liron Marcus which is available to fieldservicenews.com subscribers within our premium content library... 

---

Sponsored by: 

 

 

---

Data usage note: By accessing this content you consent to the contact details submitted when you registered as a subscriber to fieldservicenews.com to be shared with the listed sponsor of this premium content who may contact you for legitimate business reasons to discuss the content of this content.   

---

 

In the second article in our current series of articles from field service solution provider Astea focussing Artificial Intelligence and Machine Learning we explore how and why field service companies are adopting these emerging tools... 

---

Is Machine Learning a key topic for your organisation?!

There is a detailed white paper on this topic authored by Emily Hackman and Liron Marcus which is available to fieldservicenews.com subscribers within our premium content library... 

---

Sponsored by: 

 

 

---

Data usage note: By accessing this content you consent to the contact details submitted when you registered as a subscriber to fieldservicenews.com to be shared with the listed sponsor of this premium content who may contact you for legitimate business reasons to discuss the content of this content.   

---

 

There is a lot of buzz around machine learning and AI in the field service industry, but are service organizations actually adopting it? How are they applying the concepts to their business operations? And lastly, what results have they experienced thus far? We turn to some of the predominant service management industry analysts to help answer these questions.

Let’s tackle adoption trends first. Gartner predicts that by 2020, 10% of emergency field service work will be both triaged and scheduled by artificial intelligence, up from less than 1% in 2017. (1)

And by 2022, Gartner predicts that one- third of complex field service organizations will utilize machine learning to predict work duration and/or parts requirements, rising from less than 2% today. (2)

In addition to analyst predictions, another way to look at adoption trends is to ask how many companies plan to deploy machine learning in the near future. In a recent Gartner survey of 50 leading field service organizations, over 25% indicated they had artificial intelligence or machine learning projects planned for the next 12 to 18 months. (2)

Aberdeen Group’s research is in alignment with Gartner’s. According to a recent survey of customer experience management leaders by Aberdeen, only 14% of their organizations were currently using machine learning and only 9% were using AI. Yet 40% of the surveyed companies are planning to deploy machine learning and 34% are planning to deploy AI.

 

Adoption Results:

How have service companies applied intelligent systems to their operations? What have their results been thus far? 

Again we turn to the analysts at Gartner who state that field service companies will use AI and machine learning in their customer service channels to gain better insights, increase self-service and improve productivity.

Specific AI applications in customer service include:

• Intelligent case management routing and workflow;
• Robotic process automation (RPA) tooling;
• Knowledge management;
• Chatbots, virtual personal assistants (VPAs) and natural language processing (NLP);
• and finally, sentiment analysis and emotional detection in social media.(2)

Customer service appears to be the most popular application thus far for field service, but what other business functions could AI improve? According to Aberdeen, another application is managing the customer experience. Retaining existing clientele is top-of-mind for almost all companies. In fact, companies using cognitive technologies achieve 6.5 times greater year-over-year increase in customer retention rates, compared to all others.(3)

We’ve seen positive results from AI and machine learning when applied to customer service and the customer experience. But can these technologies improve life for your employees, too? 

Striking a balance between positive results for your customers and your employees is a best practice you’ll hear often when reading about cognitive technologies. The early adopters have proven it’s possible. Aberdeen’s research shows that companies using cognitive technologies enjoy 81% greater year-over-year increase in employee engagement. This is a bit of a paradox since in the short-term, some employees will be replaced by robots. Yet, when looking at the big picture it’s clear that the large scale impact of AI and machine learning will be improving employee productivity.(3)

 

Can this lead to financial success as well?

Thus far we’ve discussed positive results for your customers and your employees, but can cognitive technologies help drive financial success also? Absolutely!

Aberdeen’s data shows that companies using cognitive technologies enjoy 36% greater year-over-year increase in annual company revenue, compared to All Others. They also attain 63% greater annual improvement in customer lifetime value, compared to others.6

Companies using cognitive technologies enjoy 36% greater YoY increase in annual company revenue. They also attain 63% greater annual improvement in customer lifetime value.

 

---

 

References::

1. Robinson, Jim et a “Critical Capabilities for Field Service Management.” Gartner, 27 March 2018.
2. Huang, Olive et a “Predicts 2019: CRM Customer Service and Support.” Gartner, 13 Dec 2018.
3. Minkara, Omer. “Cognitive Customer Experience: The Future is Here.” Aberdeen Group, April 2017.

 

---

Do you want to know more?!

There is a detailed white paper on this topic authored by Emily Hackman and Liron Marcus which is available to fieldservicenews.com subscribers within our premium content library... 

---

Sponsored by: 

 

 

---

Data usage note: By accessing this content you consent to the contact details submitted when you registered as a subscriber to fieldservicenews.com to be shared with the listed sponsor of this premium content who may contact you for legitimate business reasons to discuss the content of this content.   

---

 

In a new series of articles from field service solution provider Astea, we tackle one of the burning questions being discussed amongst field service companies across the globe - what is Machine Learning and more importantly how can it be leveraged to improve service delivery? 

---

Is Machine Learning a key topic for your organisation?!

There is a detailed white paper on this topic authored by Emily Hackman and Liron Marcus which is available to fieldservicenews.com subscribers within our premium content library... 

---

Sponsored by: 

 

 

---

Data usage note: By accessing this content you consent to the contact details submitted when you registered as a subscriber to fieldservicenews.com to be shared with the listed sponsor of this premium content who may contact you for legitimate business reasons to discuss the content of this content.   

---

 

There's probably no singular definition that would be accepted universally, but there are certainly some basic concepts. To understand those concepts, think about what machine learning actually does. The machine finds patterns in the data and uses these patterns to predict the future.

For instance, suppose that we have a data-set of one million emails that were tagged as spam. We could find patterns in that data-set that characterize spam, for example emails with all caps or with exclamation points, especially when they’re in the subject line.

Then, we can use those patterns to predict whether or not an email is spam.

 

Is Machine Learning the Same as Artificial Intelligence (AI)?

These two terms are often used interchangeably, but technically they do not mean the same thing, nor are they used for the same purposes.

We will start by defining artificial intelligence (AI) since machine learning has developed as a result of breakthroughs in the AI field. AI means that machines can perform tasks in “intelligent” ways instead of just being programmed to do a single task over and over. Performing a task intelligently implies that machines can adapt to different situations. Machine learning is considered to be a branch of AI, and it means that machines can be built to learn on their own and automatically improve their decision making through experience, all without human supervision.(1)

If you’re still a little fuzzy on the differences, we will define both concepts more simply:

• Machine learning consists of technology applications that learn by analyzing a pattern of historical and recent data.
• Artificial intelligence consists of technology applications that provide automated reasoning and decision-making capabilities. (2)

 

Origins of Machine Learning and AI

If you are wondering when these concepts were created, you can look all the way back to the original logical machines--computers. The computer’s end goal was that it could eventually function like a human brain. As we learn more about how the human brain works, we build that knowledge into artificial intelligence. And when you couple our deeper understanding of how the brain works with the massive amounts of data that the internet provides, you understand why AI and machine learning have grown so much in the last few years. 

According to AI expert Terrence Mills, “These two breakthroughs made it clear that instead of teaching machines to do things, a better goal was to design them to "think" for themselves and then allow them access to the mass of data available online so they could learn.” (1)

 

Why is Machine Learning so Popular These Days?

It’s all about data. Today, data is all around us. We are living in a data-driven world that’s only going to produce more and more data as time goes on. Humans and machines have become “data generators” that produce a tremendous amount of data every second. The amount of data created in the past few years is more than ever in the history of mankind and it is growing at a rapid pace.

The digital universe doubles in size every 2 years. By 2020, it will contain nearly as many digital bits as there are stars in the universe. 

In fact, the IDC estimates that by the year 2020, the accumulated volume of data will increase to roughly 44 trillion GB.(3)

---

References::

1. Robinson, Jim et a “Critical Capabilities for Field Service Management.” Gartner, 27 March 2018.
2. Minkara, Omer. “Cognitive Customer Experience: The Future is Here.” Aberdeen Group, April 2017
3. Turner, Vernon. “The Digital Universe of Opportunities: Rich Data and the Increasing Value of the Internet of Things.” EMC Digital Universe with Research & Analysis by IDC, April 2014.

 

---

Do you want to know more?!

There is a detailed white paper on this topic authored by Emily Hackman and Liron Marcus which is available to fieldservicenews.com subscribers within our premium content library... 

---

Sponsored by: 

 

 

---

Data usage note: By accessing this content you consent to the contact details submitted when you registered as a subscriber to fieldservicenews.com to be shared with the listed sponsor of this premium content who may contact you for legitimate business reasons to discuss the content of this content.   

---

 

If there is one industry that should be leveraging data in every way possible, it’s telecommunications. The telecommunications industry services billions of people each day, generating massive amounts of data. Though not many telecom companies are leveraging this data, the introduction of data science, machine learning, and artificial intelligence in this industry are inevitable.

A study by McKinsey, Telcos: The Untapped Promise of Big Data, based on a survey of leaders from 273 telecom organizations, found that most companies had not yet seriously leveraged the data at their disposal to increase profits. And only 30 per cent say they have already made investments in big data.

So while there is certainly debate within telecom companies about whether the return on investment is worthwhile, there is no doubt that data science, machine learning (ML), and artificial intelligence (AI) are inevitable when it comes to the industry’s future. Those that figure out how to leverage these techniques and technologies will thrive; those that don’t will be left behind.

By using data science, machine learning, and artificial intelligence strategies, telecommunication companies can improve four areas of their services.

The importance of data science, ML, and AI to the telecom industry will likely present itself in these four areas in particular, which this paper will take a look at individually:

 

1. Troubleshooting:

One of the major challenges for telecom providers is being able to guarantee quality service to subscribers. Analyzing call detail records (CDR) generated by subscribers at any given moment of the day is key to troubleshooting. However, CDRs are challenging to work with because the volume of data gets massive and unwieldy quickly. For example, the largest telecommunication companies can collect six billion CDRs per day.

With data science, machine learning (ML), and artificial intelligence (AI), companies can instantaneously parse through millions of CDRs in real-time, identify patterns, create scalable data visualizations, and predict future problems.

 

2. Fraud Detection: 

Verizon estimated in 2014 that fraud costs the telecom industry upwards of $4 billion a year. However, the faster that telecom companies analyze large amounts of data, the better off they are in identifying suspicious call patterns that correlate with fraudulent activity.

Cutting-edge ML and AI strategies like advanced anomaly detection make it much easier for telecommunication companies to identify “true party” fraud quickly.

 

3. Marketing:

The high churn rate in telecommunications, estimated at between 20-40% annually, is the greatest challenge for telecom companies. Telecommunication companies can use data to build better profiles of customers, figure out how to best win their loyalty (in the most scalable and automated way), and adequately allocate a marketing budget. With improved data architecture, they are able to harvest and store a greater diversity of data that provide insights into each customer such as demographics, location, devices used, the frequency of purchases, and usage patterns. By combining data from other sources like social media, they can have a stronger understanding of their customers.

Using machine learning gives a more accurate picture of which channels are most responsible for customer conversions for better ad buying as well.

 

4. Customer Experience: 

Telecommunication companies can enhance their services by analyzing the millions of customer complaints they get every year to figure out which types of improvements will have the greatest impact on customer satisfaction and thereby increase customer retention. They can also leverage data at a larger and more automated scale to gain insights into the performance of their technicians.

The more that telecommunication companies can analyze data on customer calls, the more they can begin to recognize which types of problems are most likely to lead to unwarranted “truck rolls” and put in place measures to prevent those calls. Given the number of calls and the depth of analysis required, this necessarily dictates a machine learning approach - more specifically, a deep learning approach. Because analyzing the calls themselves means dealing with lots of unstructured data, it’s the perfect place to expand into ML and deep learning for big gains.

 

The future of data in the telecom industry

Data science is already a big part of the telecommunications industry, and as big data tools become more available and sophisticated, data science, ML, and AI will all continue to grow in this space.

In the coming years, companies that succeed will be those that figure out how to best use the massive number of data points that are flowing both through their network and around it to reduce labor costs, develop better technology and, to better understand what the seven billion potential customers around the world want to do with their smartphones and computers.

To learn more, download the whitepaper White Paper: Top 4 Growth Areas of Machine Learning in Telecommunications.

---

 

Be social and share

Atos, a global leader in digital transformation today announces that it has been identified as a ‘Leader’ by global research and advisory firm NelsonHall in its latest Vendor Evaluation & Assessment Tool (NEAT) for Cognitive IT Infrastructure Management...

Atos supports businesses in their digital transformation by providing the tools, services and consulting to enable them to successfully implement next-generation IT infrastructure and workplace services, such as those which use Artificial Intelligence (AI), cognitive, machine learning, deep learning, virtual agents, advanced analytics and robotics.

Atos’ brand new Codex AI Suite, announced recently, supports businesses and research institutes in the development, deployment and management of AI applications. It offers an easy-to-use, efficient and cost-effective solution to rapidly build and deploy AI applications, better extract value from data and develop new business opportunities.

Atos’ end-to-end Digital Workplace offering includes a range of intelligent solutions to enhance the user experience.Atos’ end-to-end Digital Workplace offering includes a range of intelligent solutions to enhance the user experience. This includes the Atos Virtual Assistant (AVA), which leverages Cognicor’s next-generation AI engine, to offer help and support for users, resulting in reduced downtime, increased user productivity, and cost reduction.

Commenting on this ranking, John Laherty, Senior Research Analyst at NelsonHall, said: “Atos is driving digital transformation across both infrastructure and service desk to improve business outcomes and end-user experience; it is embedding automation into all its standard infrastructure managed services offering for clients.”

Elaborating on Atos’ role as a leader in Cognitive IT Infrastructure Management services, Peter Pluim, Head of Infrastructure & Data Management at Atos, said: “We are delighted to be recognized as a Leader in Cognitive IT Infrastructure Management by NelsonHall. We offer an end-to-end approach to automation and robotics, thereby reducing costs, increasing quality, and creating differentiation with real-time insight for our clients.”

Be social and share