Idiro researcher holds seminar on Social Network Analysis in telecommunications

Academic research has always been important to Idiro – that’s how we became world leaders in the application of Social Network Analysis (SNA) techniques to telecommunications business problems.  It is also why our CEO is on the board of CeADAR, the Irish Centre for Applied Data Analytics Research.

So we are happy to report that our colleague Davide Cellai, who has been working on advanced uses of SNA in solving telecommunications business problems, this week gave a seminar at the University of Aalto, Finland on his advanced SNA churn research.  Davide says:

“Last Thursday I was invited to give a seminar at the University of Aalto, near Helsinki. This week, I have been hosted by the group of Jari Saramaki and Kimmo Kaski, who were possibly the first researchers to focus a research group in social network analysis applied to telecommunications, several years ago. I presented our work on port-out churn, plus some percolation models of robustness of infrastructures I have been involved with in recent years.  Here are some examples:

Social Network Analysis in telecommunications - research by Idiro Analytics
Distribution of fraction of time two subscribers spend speaking to each others in an interval of 12 weeks

In order to profile the type of connection between pairs of subscribers, we calculate the amount of time two individuals spend at peak (i.e. during working hours) and off-peak time of the day. For each pair, we can evaluate if conversations occur mainly at peak or off-peak time and give a score accordingly. In the first figure, we show the distribution of this score over all the phone calls that occurred in a period of 12 weeks. We can see two strong peaks, representing calls occurring exclusively off-peak and at peak times, respectively. We also show an enlargement of the central zone, with a broad hill representing pairs of subscribers who speak both at peak and off-peak time. This polarization suggested us to identify three layers of acquaintances: peak, off-peak, and mixed peak/off-peak.

Social Network Analysis in telecommunications - research by Idiro Analytics
Probability that a subscriber churns as a function of churning subscribers in her network of social acquaintances
This plot shows the probability that a subscriber churns after m_out of her friends have churned in a recent time interval. Generally speaking, we can see that a subscriber with more churning friends is more likely to churn, as the red crosses tend to grow with m_out. Moreover, we can see that the probability of churning is higher for the mixed peak/off-peak layer (purple boxes), meaning that at this level of relationships, churning propagates more easily.
The seminar participants were quite interested in the way we could identify types of social acquaintance based on the time of calls. They also suggested that exposure to churn in terms of duration, instead of number of churners, would improve the sensitivity of the method. In particular, Jari Saramaki, who has also experience in the data analytics industry, envisions that machine learning methods should be fed with this kind of insightful social network information to produce best lift.

The week I have spent here has been very useful. For example, researchers have shown me a method to identify families that doesn’t use any community finding algorithm, and a way to map a temporal network into a network of events, that can be treated with a known formalism. Another post-doc is working with psychiatrists to detect the onset of a mental disorder in the pattern of social activities of a person. Finally, it has been also interesting to hear that a few students or post-docs are starting a company. Best of luck, and thank you Aalto!”

Idiro gratefully acknowledges the support of Science Foundation Ireland in this work.  Idiro works with telecommunications companies across the world, helping them with customer retention, customer acquisition etc.  To learn more about Idiro’s work on Social Network Analysis in telecommunications, or to find out how Idiro helps telcos to get better marketing results through our SNA models, contact our experts.

Idiro Analytics to speak at National Conference on Cloud Computing & Commerce

Idiro’s Simon Rees has been invited to speak at Ireland’s National Conference on Cloud Computing and Commerce in Dublin City University on the 14th of April 2015.

NC4 logo 2015

Simon will speak on ‘Analysing customer networks for influencer marketing’ within the conference’s Analytics track.  He explained: “It is an honour to be invited to address this conference.  This talk will focus on Idiro’s pioneering work on Social Network Analysis – but with a heavy emphasis on bringing business value through advanced analytics.  This talk is aimed at businesses that wish to gain competitive advantage through big data analytics”.

To register for the conference, visit http://www.nc4.ie/.

Join Idiro at Mobile World Congress 2015 this March

MWC 2015 Logo

Idiro are thrilled to announce that we will be attending this years GSMA Mobile World Congress event in Barcelona with our partners, Apliman, from March 2-5.

MWC, ‘the world’s greatest mobile event’, acknowledges and showcases that we, as an industry, are on ‘The Edge of Innovation’ and this is something that resonates strongly with all of us here in Idiro. We are constantly striving to be innovative, original and efficient in our approach to understanding our customers and their needs.

If you would like to arrange a meeting with us during the first two days of the event (March 2-3), please contact our Analytical Solutions Manager, Clare Curtin, who will be happy to accommodate you.

You can contact Clare via: clare.curtin@idiro.com

Alternatively, you can find us on the Apliman stand in Hall 5, Stand 5G23.

See you in Barcelona!

Some research tidbits for Christmas

Over the last couple of weeks a few interesting research items on social psychology and social network analysis have crossed our desks – so we have compiled them into this collection of research tidbits for Christmas.  Enjoy!

In-flight influence

The power of influence, in-flight
People near us influence our in-flight purchases

First up, a study that shows how the decisions of people around us influence our decisions, even if we don’t know the people.  This elegant piece of analysis, written up in this working paper and covered by the Washington Post (albeit with a misleading headline) shows how our decisions about whether to purchase in-flight food and drink are influenced by those around us.   Because the study had access to reservations data, it was able to exclude groups travelling together, and control for parameters such as seat choice.

The research found that people sitting near other purchasers were 30% more likely to make in-flight purchases.  If this is the the level of influence that strangers hold over us, how much more is our behaviour influenced by those who we care about?  Answer: in Idiro’s experience, lots.

The same Washington Post article referred to an interesting piece of research demonstrating the power of peer pressure in schools.  Message to all parents: make sure your kids are in classes with people cleverer and more diligent than them.

A link analysis of languages

Multi-lingual Wikipedia editors: which languages?
Multi-lingual Wikipedia editors: which languages?

There are plenty of studies showing how which languages are spoken by the greatest number of people, which languages are economically the most powerful – but which languages serve as the pivots between other, less popular languages?  To put it another way, if you speak a minority language (like Welsh) and want to understand it written in another (e.g. Kikuyu), which other languages are necessary to make the link?  In this case, most Welsh speakers know English, as do many Kikuyu speakers – so the answer is simple: just English.

Quartz published details of an interesting MIT study looking at this in depth, using three data sources: multi-lingual Wikipedia editors, multi-lingual Twitter accounts, and book translations.  The data is displayed in an interactive website but it’s worth watching this video, as it’s a complex enough study.

One can criticise the data sources, of course (for example, the great firewall of China restricts Chinese Twitter usage) but nevertheless it’s a fascinating topic.  Here in  multi-cultural Idiro, the most common hub language is English (of course), followed, we observe, by Russian.

How many friends?

How many people do we have contact with through our mobile phones?  Idiro’s researchers took a week’s worth of connection data from a European mobile phone network, and counted the number of different phones that each person had contact with over a week.  We then plotted the distribution of the number of contacts each phone had – in other words, the total number of links per person.  As the graph shows, a number of phones were (as one would expect) used rarely or not at all that week.  A few users made over sixty unique connections in a week, and a large number of people made between 5 and 15 connections.  We compared Christmas with an average summer week. and found – no surprise – that people make more connections over Christmas week, as we renew old friendships.

Distribution of the number of mobile contacts per person
Distribution of the number of mobile contacts per person

Finally, here is a study by Hill and Dunbar demonstrating that Christmas card networks are (or were, when we used to send Christmas card to all our friends) a reasonable approximation of Dunbar’s number – 150.

Merry Christmas to all, from the Idiro team

People and data; a truly symbiotic relationship

141201.unbiased

We need data and it needs us. Every day, businesses are using data to learn more about their customers, better-target their marketing campaigns and increase their ROI. The right data can do a lot for your business, but without the right people to analyse, interpret and utilise it, your business goals can suffer.

A problem users of data face sometimes is that they are guilty of ‘cherry-picking’ the data they need to support ideas and opinions that they already have. As put in this article by Tom Fishburne: “Data doesn’t have biases. It’s people who collect and select the data who bring bias to it.”

It’s imperative to your business goals that you and your business are using your data as effectively and efficiently as possible. Here at Idiro, we not only have the skills to turn your data into actionable insights but we also have the perfect people to help you use your data to it’s highest potential.

We’ve placed SNA consultants in companies with excellent results. To learn more about our SNA Consulting services, please contact us at: experts@idiro.com

 

Idiro Announces Partnership with Newtoms

MEDIA RELEASE

Atlanta & Dublin – 28th October 2014

NEWTOMS and Idiro Technologies Announce Partnership

Winston Rivero & John Dunne

Pictured L-R: Winston Rivero, co-Founder and Executive Director & John Dunne, Idiro Chief Commercial Officer

NEWTOMS, Subject Matter Experts and leading provider of specialized professional services related to Data Collection-Mediation, and Idiro Technologies, a leading provider of advanced data analytics and pioneers in Social Network Analysis Technology today announced a partnership.  This partnership gives NEWTOMS the right to offer Idiro’s services in the Latin American markets and strengthens its Mediation, Insight, Action orientation around CDR Analytics and Telco Industry; similarly the alliance gives Idiro Technologies the right to offer NEWTOMS’s specialized professional services related to Mediation and Interconnect billing solutions already widely deployed in Europe today.

Idiro’s advanced Social Network Analysis (SNA) platform helps Telco Marketing, Anti-fraud and Customer Experience staff to segment and target customers. Idiro uses voice, SMS and data traffic call detail records to build up a detailed picture of the social communities within the customer base. Idiro’s analytics are predominantly used to improve customer acquisition and customer retention and to increase ARPU via cross sell/upsell opportunities. Idiro SNA’s analytics focuses on the relationships rather than the individuals – the right approach for the emerging markets where the pre-paid customer is predominant and the information available about pre-paid customers is scarce.

According to Winston Rivero, co-Founder and Executive Director of NEWTOMS, “This partnership will draw a combination of technology, services and skills from NEWTOMS and IDIRO to help operators GET subscribers, RETAIN them, GROW ARPU.”

By combining NEWTOMS’s specialized professional services with Idiro Technologies’ SNA platform, telco customers will mine data from their existing Mediation systems and draw insights from CDRs via SNA technology. This will allow the telco to identify influencers, predict churners, and select targets for successful acquisition and cross-sell campaigns.

Winston Rivero & John Dunne

Pictured L-R: Winston Rivero, co-Founder and Executive Director & John Dunne, Idiro Chief Commercial Officer

According to both parties, this partnership will prove to be most beneficial, as each company’s solutions complement the other. As stated by Winston Rivero, co-Founder and Executive Director of NEWTOMS, “By offering NEWTOMS-IDIRO synergies, we will help our clients to successfully mine their ever-growing amount or CDRs and their rich mine of traffic data, gain competitive insights by identifying key influencers in their networks and execute successful word-of-mouth campaigns, member-get-member strategies, churn reduction and finally improve their EBITDAs.”

According to John Dunne, Idiro Chief Commercial Officer, “NEWTOMS is an ideal partner for IDIRO; they have an excellent track record in Latin America, they are subject matter experts on the existing data collection and mediation system and Interconnect billing solution already deployed in more than 50 sites in Latin America, they are experts offering Mediation, Insight, Action and by combining our award-winning technology and NEWTOMS expert services, we can, together, help mobile operators turn raw data into actionable insights, therefore enabling fruitful action. By integrating IDIRO’s SNA platform with NEWTOMS services, we are now in a position to offer mobile operators an end-to-end solution that will positively impact their bottom-line”.

About Idiro

Based in Dublin, Ireland, Idiro Technologies is an award-winning provider of marketing analytics to service providers and businesses around the world.  Idiro specialises in advanced predictive analytics for telecoms and online gaming companies and is a recognised leader in ‘Big Data’ analytics consulting and the commercial deployment of social network analysis technologies. For an overview of Idiro’s social network analysis technology, watch the short video on the Idiro homepage at: www.idiro.com

About Newtoms

NEWTOMS professional services have helped leading operators in Latin America with key-strategic Data Collection-Mediation that have enabled them to launch services such as LTE, SMS, VAS, incorporate new network elements, feed downstream systems and improve CDRs visualization to Financial Executives. NEWTOMS has offered Mediation, Insight, Action to major Telco Groups in the region including largest Operators in Peru, Panama, Venezuela just to mention a partial list.

Media Contact Information

Simon D Rees, Clients & Marketing Director, Idiro Technologies.

+353 87 240 5999

simon.rees@idiro.com

Winston Rivero, co-Founder and Executive Director

+1-678-736-3022

winston.rivero@newtoms.com

Idiro CEO Aidan Connolly speaks at CeADAR ‘Big Data’ events in Dublin & Cork

CeADAR, the Centre for Applied Data Analytics, has held a series of open days in Dublin and Cork, focused on demonstrating how it can transform information or ‘big data’, into insight and into value for its industry partners.

The event entitled ‘Big Data Analytics: Technology’s Hottest Trend’ included a series of prototype demonstrations along with a numbers of speakers from industry and academia.

CeADAR is an industry-led Technology Centre for the development and deployment of analytical technology and innovation and is headquartered at NexusUCD, the Industry Partnership Centre at University College Dublin.

Aidan Connolly Speaking at CeADAR/UCD 'Big Data' event

Aidan Connolly, CEO, Idiro said, “Initiatives like CeADAR ensure that big data analytics continues to move in the right direction. CeADAR’s work is imperative to the success of new developments in the industry. We are delighted to be working with both CeADAR and University College Dublin and predict great success in our future endeavours.”

Aidan Connolly spoke about Idiro’s joint research project on multi-SIM behaviour, as well as appearing on a panel of experts to answer questions about the biggest challenges facing the industry today.

Full article on the events here.

For more information on CeADAR, see here.

Measuring ROI Of WOM Marketing

AT&T’s Greg Pharo recently joined Ed Keller of the Keller Fay Group for a webinar on the Return-On-Investment of Word-Of-Mouth (WOM) marketing. He shared insightful information on AT&T’s research into WOM and the significant role it plays in driving new customer acquisition.

Keller stated at the beginning of the webinar that in a recent study, approximately 85% of marketers in the US couldn’t show the ROI of WOM marketing, despite plans to increase their budget spend in the category. A McKinsey article also noted WOM as being the most ‘disruptive’ marketing factor, adding that WOM is responsible for 2.1 billion daily brand impressions in the US and 440 million in the UK.

One particularly interesting statistic was that of the 90% of WOM marketing that happens offline (which is interesting in itself), over half of this was driven by one or another form of marketing or media. Of particular importance is the fact that 26% was driven by paid advertising. Targeted advertising is obviously a vital factor in driving sales through WOM and on the back of that, identifying who to target remains an increasingly important challenge. Being specialists in advanced and predictive analytics, Idiro can identify propitious customer segments so that marketers can better target their campaigns, in order to capitalise on these new figures emerging from AT&T’s research.

Although paid media remains the primary driver of sales for AT&T at 30%, WOM is a close second. Pharo elaborated on this by saying that WOM explained over 10% of sales through positive comments, but also over 10% of lost sales through negative comments.

 
ROI Of WOM

He concluded his thought-provoking presentation by saying that WOM metrics belonged on a CMO dashboard as a KPI and that WOM is ‘an impactful, relevant variable for influencing sales in the Wireless industry’. He believes that conversation should be a marketing objective for all marketers and Ed Keller went on to explain the best ways for those marketers to stimulate WOM:

1. Focus on ‘talk-worthy’ messages, i.e. ‘triggers

2. Target consumers who can carry messages, i.e. ‘influencers

3. Favour marketing/media that maximises WOM, i.e. paid advertising

He also added an interesting point at the end that maybe all media should be thought of as ‘social’.

Idiro’s expertise in predictive analytics can provide marketers with a thorough analysis of their target audience, identifying the key influencers amongst communities and even amongst families and households. Using the SNA Plus platform, marketers can really take full advantage of the power of WOM, which, if this webinar is anything to go by, will remain a key sales driver for years to come.

Contagion of marriage, divorce, and mobile phone decisions

Yours truly went to a wedding last weekend. Many of us go through a stage where we go to half-a-dozen weddings in a year, as our friends all seem to get hitched within a couple of years of each other.   And great fun it is too.  There is some anecdotal evidence getting married is contagious – perhaps attending the wedding makes one’s own nuptials more urgent (for the woman) or inevitable (for the man)?  Perhaps when one’s friends do it, the logistics start to feel doable.  The tragic phenomenon of copycat suicide is well known in academia, and media guidelines have been developed (e.g. here) to minimise contagion through sensitive reporting. There is some interesting evidence that divorce is contagious – as this Pew Research report says:

A research team headed by Rose McDermott of Brown University analyzed three decades of data on marriage, divorce and remarriage collected from thousands of residents of Framingham, Massachusetts.

McDermott and her colleagues found that study participants were 75% more likely to become divorced if a friend is divorced and 33% more likely to end their marriage if a friend of a friend is divorced

Contagion of marriage, divorce, and mobile phone decisions

Though the study has attracted some criticism (for example, here), it certainly passes the intuitiveness test – our experience tells us that there’s some truth in it.  More research will certainly follow, to test and refine the conclusions. Maybe the reason that we observe weddings happening in clusters is – in part – because for many couples they are linked to a time of life, like getting your first job or having a first child.

Many years ago, when the author worked in a telco, we commissioned research on consumer attitudes to prepaid and postpaid mobile.  The research found that the consumers viewed prepaid mobile service like having a casual boyfriend / girlfriend – and postpaid contracts like marriage.  The difference was in the level of commitment. Idiro’s research in more than one market has found that moving from a prepaid to a postpaid contract is contagious too – when your friends move to postpaid, you become much more likely to follow suit.  (Idiro’s customers use this information to improve success rates in prepaid-to-postpaid migration campaigns.)  We believe that whereas this contagion used to be just down to customers moving together from a short-term to a long-term view of their world, nowadays the contagion is also heavily influenced by smartphone envy.  We know that smartphones are highly contagious – and customers choose postpaid contracts in order to finance expensive smartphones. Our friends influence us more than we think – often subconsciously.

So, we know that there is strong evidence for contagion of marriage, divorce, and mobile phone decisions.  As humans it’s good to be aware of these influences – so we can manage the pressures towards marriage, divorce, or whatever.  For the telco, Idiro’s algorithms hold the opportunity for the telco to get better marketing returns by targeting the right customers for these offers.

How to run a successful trial of Social Network Analysis for marketing

At this stage, everyone in marketing understands the power of word-of-mouth – which Tom Fishburne’s cartoon, below, elegantly illustrates. Organisations with link data – telcos, gaming companies, social networks and the like – can take a scientific approach to word-of-mouth marketing (aka influencer marketing) by deploying Social Network Analysis algorithms to target the influencers – or the influenced.   Idiro is a pioneer in this space.

Over the past few weeks we have been talking with two mobile operators who, prior to talking to Idiro, had each run projects to evaluate the benefit of Social Network Analysis (SNA) for improving targeting in marketing.  However, in both cases the trials ran into difficulties that could have been avoided. At the end of the projects both mobile operators had invested significant time and money in running a trial, but neither was in a position to make an investment decision.

We’ve been involved in mobile operator trials of Social Network Analysis for over eight years, and we’ve seen the good, the bad and the downright ugly – so we know how to run a successful trial of Social Network Analysis for marketing. Here are eight tips to help you run SNA trials that give you a clear evaluation of SNA for your business – quickly and efficiently.

1. First, be really clear on your objectives

It might sound obvious – but are you proving a technology, evaluating a vendor or trying to find the best way solve a business problem? Be really clear on this, both internally and with your SNA trial vendor(s). Also, how serious is your organisation about adopting a SNA solution if the trial succeeds?  We evaluate operators who come to us looking for SNA trials on 2 axes:

  • To what extent are the key sponsors prepared to accept the concept behind SNA for marketing?
  • The degree of organisational backing / commitment to deploying a SNA solution if it is proven (worst case: a solo run, best case: a project with board backing)

Make sure your organisation is prepared to invest in a solution before you start your evaluation of SNA.

2. Work out the evaluation, decision and implementation steps in advance

A common cause of trials not completing successfully is that the assessment of SNA that they deliver is not what the senior team needs in order to make the investment decision.  Therefore, before you finalise the trial, work out the evaluation process and success criteria. We offer our customers help with evaluation methodologies for SNA in marketing.

3. Design the trial carefully based on your objectives and your approval process

Many mobile operators make the mistake of specifying too much technical detail (while leaving the business success criteria too loose).  Others base their trial design on the offering from a particular vendor. We all know which vendor will perform best in a trial like that!

Different SNA solution vendors have different philosophies, and it is usually best not to specify the vendor’s methodology or business model tightly, at least initially, and focus on the business benefits that are required (see point 1). That way, a wide range of vendor approaches can be tested – and ideas that you did not think of can be incorporated into your project. Use the agreed evaluation method and success criteria to inform the key elements of the scope:

a) Live or historical trial, or both? b) Role and design of control groups c) Technical  / operational models to be considered (Saas, managed service, software licence, etc.)

These are important choices, and they will affect the outcome of your trial.

4. The farmer and the cowman should be friends

The most successful SNA implementations tend to have close cooperation between marketing and analytics teams. Whichever side of the organisation you work on, bring your colleagues on board early.

5. Get the trial campaign right

Because they target the influencers or the influenced in your customer base, word-of-mouth campaigns need to be designed carefully. If your evaluation involves a campaign, don’t put all your effort into the technology and test it on a bog standard campaign.  Idiro are experts in word-of-mouth campaigns.

6. Budget

Be realistic about how the relationship between spend and quality. Most vendors want to cover their costs at least, during the trial. You could doubtless persuade one or two vendors to work for free, but this might mean that you exclude the best vendors. Remember also to budget for internal costs.

7. Fix a realistic timescale

SNA trials with thorough methodologies take time to do properly. Trials with highly aggressive deadlines nearly always overrun – typically because one or more internal tasks do not receive the priority they need. Set realistic deadlines and make sure your internal project manager has the authority to get the tasks done.  Beware of shortcuts, particularly around evaluations.

8. A successful introduction of new technology requires change in the organisation, which isn’t easy

A successful post-trial implementation leading to a strong ongoing ROI depends on getting a number of factors right – operational, analytical, process change, KPIs, etc.  When post-trial implementations fail, they do so because they don’t address these difficult issues or don’t have a strong leader keeping the focus on the benefits.  Once the SNA trial is completed, the benefits are proven and the contract is signed, make sure you task the team with delivering the benefits within (say) 6 months and not just completing the implementation project.

 

Idiro would be happy to expand on any of these points.  If you are planning a trial of Social Network Analysis solutions for marketing, feel free to run your ideas by us. We might save you some heartache.