Tagged: Network Toggle Comment Threads | Keyboard Shortcuts

  • admin 9:53 am on August 6, 2016 Permalink
    Tags: , Corp., , , Network, , Robust, , , , ,   

    Saudi Telecom Corp STC uses the Internet of Things to provide robust network and customer centric services 

    Teradata Videos

  • admin 9:51 am on December 19, 2015 Permalink
    Tags: , , , , Network, , , ,   

    Winners Named in Teradata University Network International Big Data Talent Competitions 

    Teams from Australia, Thailand and the US prove their analytics prowess
    Teradata News Releases

  • admin 9:52 am on October 19, 2015 Permalink
    Tags: , , , Network, , , unlocks,   

    How TURKCELL Unlocks Customer Value From Network Performance Analytics 

    At the annual Teradata Partners 2015 conference (happening this week at the Anaheim Convention Center) a big point of conversation among data scientists, business analysts and executives alike is advanced analytics.

    The sessions on this topic are many. For mobile phone operators, for example, the success of the business is entirely dependent on customer satisfaction. As an increasingly competitive industry, if customers aren’t completely – and continuously – happy with the coverage, speed and capabilities of their mobile network provider, they’re likely to pursue other options. So, how do mobile operators continue to stay ahead of the curve while ensuring that each customer in their network is continuously pleased with their service? Simple: advanced analytics.

    This is specifically the case for TURKCELL, a leading mobile phone operator of Turkey, and among the top five most valuable companies throughout the country. With  thousands of daily users, TURKCELL saw the opportunity to glean important customer experience insights from their network data. It was critical for TURKCELL to begin thinking about each individual user within the network – while he or she may not have any complaint tickets in the system, could TURKCELL confidently say that this customer is completely satisfied? Not necessarily. What was needed was a deeper understanding of this customer’s experience; TURKCELL needed analytics.

    Problems and Discoveries

    A major issue faced by mobile network providers is adapting to the fast evolving mobile environment. With the onset of mobile devices and applications, the environment has seen enormous shifts in the last five years alone. Network analytics have given TURKCELL a leg up on the competition, by providing insight into customer feedback and satisfaction during said changes, allowing the company to discover new opportunities while maintaining optimized customer experience.

    Through advanced analytics, TURKCELL was also able to nail down and rectify a slew of analytics problems that could lead to customer pain points and problems, including:

    • Volume and speed of data
    • Changing data characteristics
    • Technical difficulties
    • Resource limitation
    • Budgets
    • And more

    Customer Experience Factors

    Network analysis was also a key driver in helping TURKCELL identify factors that contribute most heavily to a customer’s overall experience with their mobile operating network. Network, device and application were determined to be the top three concerns of network customers.

    By looking at data surrounding these factors, TURKCELL was able to improve customer experience and figure out exactly what makes customers happy, and arguably more important, what makes them unhappy, so that any issues surrounding these pertinent factors can be improved upon immediately. Were customers happier after an update? Did their level of satisfaction increase alongside the improvement of coverage reliability? Using network analysis helped TURKCELL answer these questions and more.

    Enabling for Future Growth

    Through network analysis with Teradata of over 35 billion rows of XDR files, processed by the system daily, TURKCELL seized the opportunity to enable several different factors that are attributed to the company’s future growth and continued customer satisfaction.

    • Data Mining. Through data mining, the churn prediction success ratio increased remarkably. Additionally, mobile traffic was better forecasted for optimized network planning, while major costs in network investment were cut.
    • Call Center Integration. Since TURKCELL’s platform is completely customer-centric, customer quality index (CQI) sets are established and evaluated for each individual user. These evaluation results are then fed to the Call Center System and agents are immediately evaluated upon receiving a complaint. As a result, these problems occur less and less over time as call center agents become better equipped to handle them.
    • Campaign Management. Campaign target selection is empowered with exact network experience figures, helping to improve targeted campaigns to precisely augmented audience segments.

    Network analysis has already provided TURKCELL with the insights needed to make a real and lasting impact on customer engagement, experience and satisfaction. As the company continues to monitor and analyze the data provided by their network, it hopes to further enrich CQI sets, empower the platform with 4.5G data and integrate with other network operation and monitoring systems.

    The post How TURKCELL Unlocks Customer Value From Network Performance Analytics appeared first on Industry Experts.

    Teradata Blogs Feed

  • admin 9:52 am on September 24, 2015 Permalink
    Tags: , , Finalists, , , Network, , ,   

    Teradata University Network Names 13 Finalists in International Big Data Talent Competitions 

    Next phase in helping major corporations fill their big data talent pipeline to be completed in October
    Teradata News Releases

  • admin 9:47 am on July 10, 2015 Permalink
    Tags: , , , , Network, , ,   

    Social Gaming Network Use of Teradata Cloud to Enhance Customer Retention 

    Teradata White Papers

  • admin 9:51 am on March 26, 2015 Permalink
    Tags: , , Network, Pipeline, , ,   

    Teradata University Network Builds Big Data Talent Pipeline 

    Registration deadline April 1 for global business analytics competition among universities
    Teradata News Releases

  • admin 9:44 am on December 20, 2014 Permalink
    Tags: Network, Novetta, , , ,   

    Teradata and Novetta Solutions Using Your Network to Protect Your Network 

    Teradata Brochures

  • admin 9:57 am on December 11, 2014 Permalink
    Tags: , , Inaugural, , Network, , , , ,   

    Teradata University Network Names Three University Teams the Winners of Inaugural Analytics Contest 

    Showcase for the Data-Driven Workforce of the Future who are Already Solving Business Issues with Big Data and Analytics.
    Teradata News Releases

  • admin 9:54 am on December 10, 2014 Permalink
    Tags: , , IEEECS, joins, Network, Professional, , ,   

    IEEE-CS Certification and Professional Education Program Joins the Teradata University Network 

    Educational collaboration will increase skill levels and career readiness
    Teradata News Releases

  • admin 9:51 am on November 27, 2014 Permalink
    Tags: Belief, Crazy, , Graphs, Network, ,   

    A Crazy Belief: Predicting Outcomes from Network Graphs 

    September 26, 1433

    Two rival factions are attempting to seize Florence’s city hall. One block’s forces arrive haphazardly with new arrivals offset by departures. In contrast, the other block immediately and decisively mobilises all of their supporters.

    Centuries later, Medici is a household name; Albizzi, Peruzzi, and Strozzi are largely forgotten.

    Could this outcome have been predicted?

    The Medici were neither the richest, oldest, newest, largest or most popular family at the time. In fact, statistically there was no difference between Medici and oligarch “block” of families across conventional metrics. Yet the Medici won; what they had was a well-constructed network.

    Florentine history is well-recorded and studied. The seminal work of Padgett and Ansell [1] describes the data and method to construct the social network of Florence’s most prominent families at the dawn of the Medici’s ascent to power.


    Beyond usual metrics, the Medici particular skill was in their positioning within the social structure of medieval Florence. This is best illustrated by measuring the relative importance of each of the 33 families within the network, using network centrality measures: betweenness, closeness, and eigencentrality. On average, the Medici are the most central family.

    Centrality measures are calculated over the network links, but some bonds are stronger than others and Padgett distinguishes nine different types of connections classified as “strong” (marriage, trade, real estate, employment, partnership) or “weak” (loan, patronage, friendship, mallevadori [2]) ties. We consider link strength by assigning a weight of 3 to strong ties and 1 to weak ties. When two families share more than one link (eg, marriage and trade), we sum the weights to obtain the total strength of the bond.

    Wealth and centrality values for all families, (size and color have identical meaning). While of average wealth (among elite families), the Medici have the highest betweenness and closeness values, and the second highest eigencentrality, making them the best connected family.

    With the structure of the social network known, we use loopy belief propagation to predict the likelihood a family will side with the Medici during a power struggle. Initial values are set as 1 (100% sides with Medici) for the Medici themselves, and 0 (0% sides with Medici) for the Peruzzi and Strozzi families (the most prominent oligarch families). Every other family’s belief is unknown (ie, 50%) a priori.

    Belief propagation results predict that, considering families’ size, the Medici will be able to mobilize 89% of their supporters, while 65% of the other families will support the oligarch block. Historical records indicate the Medici were supported by 93% of their followers,  oligarchs by 59% of other families! This is a staggering performance considering the assumptions [3].

    Left: Seeding the Medici as 1 and Strozzi and Peruzzi as 0 shows a balance of forces broken by the Medici’s greater support from their followers (dark green). Right: If another family had risen instead, here Orlandini, the model predicts a crushing defeat.

    Given the predictive accuracy, we can look at the paths not taken. What if a more peripheral family would have tried to rise up against the oligarchs? They would have been crushed.


    The Florentine problem, while small in terms of nodes and links, is difficult to solve without appropriate software. When networks are orders of magnitude larger, such as current social networks, one needs a scalable graph processing framework to enable accurate predictions and unlock the potential of network graphs.


    [1] JF Padgett and CK Ansell, “Robust Action and the Rise of the Medici, 1400-1434”, AJoS: 1259-1319, 1993

    [2] A guarantor (effectively a medieval bail bondsman)

    [3] This kind of predictive performance based on network structure alone is only possible because the two blocks are statistically “evenly matched” on classical metrics.


    Clément Fredembach is a data scientist with Teradata Australia and New Zealand Advance Analytics group. With a background in Colour Science, Computational Photography and Computer Vision, Clement has designed and built perceptual statistical experiments and models for the past 10 years.


    Teradata Blogs Feed

Compose new post
Next post/Next comment
Previous post/Previous comment
Show/Hide comments
Go to top
Go to login
Show/Hide help
shift + esc