therevolutionof SOCIAL THERMODYNAMICS IN BUSINESS APPLICATIONSA new model to predict social changes…
What these events have in common ?Electrical & telephone bills, stock prices, frauds & deaths ratesThe Percolation theory and the nuclear multi-fragmentation The abundances of genes in various organisms and tissuesThe churn  distribution in a mobile network operatorThe density distribution  of votes in political electionsThe density distribution of urban agglomerationsThe distribution of firm-sizes all over the world The frequency of words in natural languagesThe scientific collaboration networkThe total number of cites of physicsThe Linux packages linksThe Internet traffic…… Are social events determined by universal laws ?
Unexplained Incredible FactsPhysicist John Archibald Wheeler stated that: “All things physical are information-theoretic in origin and this is a participatory universe...”
Regularity in the words frequency in natural languages and urban agglomeration was empirically already observed, about 100 years ago: The Zipf’s Law.
Benford’s Law provides results which have been found to apply to street addresses, population numbers, lengths of rivers, physical and mathematical constants, and processes described by power laws (which are very common in nature). A little bit of History… background75 years ago, George KingslyZipf (1902-1950), an American linguist and philologist who studied statistical occurrences in different languages, observed incredible regularities, not only in the  different languages but in several social distributions. Zipf was Chairman of the German Department and University Lecturer at Harvard University. He worked with Chinese languages and demographics  as well. Zipf's law states that while only a few words are used very often, many or most are used rarely, following a proportionality of this type: Pn ~ 1/na,  where Pn is the frequency of a word ranked nth and the exponent a is almost 1. This means that the second item occurs approximately 1/2 as often as the first, and the third item 1/3 as often as the first, and so on. The rank vs. frequency distribution of individual incomes in a unified nation approximates this law. Breaks in this "normal curve of income distribution" portend social pressure for change, even revolution. This is demonstrated in his 1941 book, "National Unity and Disunity" in which the break in the curve of income distribution in 1940 in Indonesia predicts revolution there. Revolution began five years later, in 1945..
Zipf’s LawZipf's law, an empirical law formulated using mathematical statistics, refers to the fact that many types of data studied in the physical and social sciences can be approximated with a Zipfian distribution, one of a family of related discrete power law probability distributions.  Up to now, it was not known why Zipf's law holds for most languages. However, it may be partially explained by the statistical analysis of randomly-generated texts.If the natural log of some data are normally distributed, the data follow the log-normal distribution. This distribution is useful when random influences have an effect that is multiplicative rather than additive. .Much of his effort could explain properties of the Internet , distribution of income within nations, and many other collections of data
Benford’s LawBenford's law, also called the first-digit law, states that in lists of numbers from many (but not all) real-life sources of data, the leading digit is distributed in a specific, non-uniform way.  According to this law, the first digit is 1 almost one third of the time, and larger digits occur as the leading digit with lower and lower frequency, to the point where 9 as a first digit occurs less than one time in twenty. This distribution of first digits arises logically whenever a set of values is distributed logarithmically.Real-world measurements are often distributed logarithmically (or equally, the logarithm of the measurements is distributed uniformly). A logarithmic scale bar. Picking a random x position on this number line, roughly 30% of the time the first digit of the number will be 1 (the widest band of each power of ten).
Benford’s LawThis counter-intuitive result has been found to apply to a wide variety of data sets. The results also hold regardless of the base in which the numbers are expressed, although the exact proportions change.It has been argued that Benford's law is a special case of Zipf's law. This special connection between these two laws can be explained by the fact that they both originate from the same scale invariant functional relation from statistical physics and critical phenomena
Fisher InformationIn mathematical statistics and information theory, the Fisher Information (sometimes simply called Information) is the variance of the score. Its role in the asymptotic theory of maximum-likelihood estimation was emphasized by statistician R.A. Fisher The Fisher information is a way of measuring the amount of information that an observable random variable X carries about an unknown parameter θ upon which the likelihood function of θ, L(θ) = f(X;θ), depends. Fisher information is widely used in optimal experimental design. Because of the reciprocity of estimator-variance and Fisher information, minimizing the variance corresponds to maximizing the information.When the linear statistical model has several parameters, the mean of the parameter-estimator is a vector and its variance is a matrix. The inverse matrix of the variance-matrix is called the "information matrix". Using statistical theory, statisticians compress the information-matrix using real-valued summary statistics; being real-valued functions, these "information criteria" can be maximized.
Dunbar’snumberDunbar's number is a theoretical cognitive limit to the number of people with whom one can maintain stable social relationships. These are relationships in which an individual knows who each person is, and how each person relates to every other person.[1] Proponents assert that numbers larger than this generally require more restricted rules, laws, and enforced norms to maintain a stable, cohesive group. No precise value has been proposed for Dunbar's number, but a commonly cited approximation is 150.Dunbar's number was first proposed by British anthropologist Robin Dunbar, who theorized that "this limit is a direct function of relative neocortex size, and that this in turn limits group size ... the limit imposed by neocortical processing capacity is simply on the number of individuals with whom a stable inter-personal relationship can be maintained." On the periphery, the number also includes past colleagues such as high school friends with whom a person would want to reacquaint themselves if they met again
Sixdegrees of separationSix degrees of separation (also referred to as the "Human Web") refers to the idea that, if a person is one step away from each person they know and two steps away from each person who is known by one of the people they know, then everyone is at most six steps away from any other person on Earth. It was popularised by a play written by John Guare.Kevin Bacon Game: The game "Six Degrees of Kevin Bacon" was invented as a play on the concept: the goal is to link any actor to Kevin Bacon through no more than six connections, where two actors are connected if they have appeared in a movie together.
Confidential and Copyrighted…  CAN SOCIAL CHANGES BE PREDICTABLE  THROUGH A WHOLE INNOVATIVE MODEL ?
Background: How it all started ?¡Based on a classical scientific process, a scientist’s curiosity him led to analyze the results of the 2008 Spanish elections and …BackgroundBipartisanshipOtherpartieswithrepresentationPartieswith no representationLn (number of votes)Based on a classical scientific process, a scientist’s curiosity led him to analyze the results of the 2008 Spanish elections and discovered that their logarithmic representation  followed , surprisingly, almost a perfect straight line.Ranking
BackgroundBased on a classical scientific process, a scientist’s curiosity led him to analyze the results of the 2008 Spanish elections and discovered that their logarithmic representation  followed , surprisingly, almost a perfect straight line.
 Such regularity drove the scientists to search for a pattern behind that behavior, and to explain how people associate to create common interests groups (clusters).Background Expecting this behavior could be exhibited in other real life events and searching for possible analogies, similar results were found in several interesting data  collections…
Like in the result of the Brazilian elections…BackgroundExpecting this behavior could be exhibited in other real life events and searching for possible analogies, similar results were found in several interesting data  collections…
Like in the result of the Brazilian elections…
and in the  population distribution in towns in different countries !!…Background: Nothing New Yet! Expecting this behavior could be exhibited in other real life events and searching for possible analogies, similar results were found in several interesting data  collections…
Like in the result of the Brazilian elections……
and in the  population distribution in towns in different countries !!…In fact, this regularity is what The Zipf’s Law had confirmed for many years.
BackgroundZipf’sLawDistribution of words
Distribution of  firmsizes
Internet trafficdistribution…Benford’sLawDeathsrate
Populationnumber
Stock Prices…
 Similar regularities have been detected in many other social events…	BUT …NOBODY HAD BEEN ABLE TO EXPLAIN  HOW or WHY  THESE REGULARITIES HAPPENED BASED ON SCIENTIFIC PRINCIPLES……AND THERE WAS NEVER A THEORY AVAILABLE TO EXPLAIN IT !!Up to now !! ...
Scientific InnovationUNIVERSAL SCALERULE Attempting to define a scientifically based framework, which would explain and predict the nature of those events, after trying different models and methodologies,  their first conclusion (based on a sound scientific empirical analysis) led to the discovery of a new completely revolutionary scientific concept…	… The UNIVERSAL SCALE RULE…  !!
Scientific InnovationUNIVERSAL SCALERULEThanks to the application of this rule, it was proven that the way people form groups of interest (clusters)  follows a pattern based on a  thermodynamic variable that was named   “COMPETITIVENESS” (λ)The pattern behind it all had just been unveiled !!
Scientific InnovationSOCIAL THERMODYNAMICS It was the first time that the Information Theory was successfully  used to explain reality and the first time that from the “Principle of Minimization of  Fisher Information” could be obtained, not only the Relativity, Quantum Mechanics, Classical Electrodynamics, Field Theory, Thermodynamics... but, as well, an innovative theory:	“Social Thermodynamics”
Scientific InnovationSOCIAL THERMODYNAMICSUNIVERSAL LAWSZipf’s Law
Benford’s Law
Dunbar’s Number
Six degrees of separation
“Competitiveness”Explains both Zipf’s Law and Benford’s Law: they naturally emerge when the correct symmetry and variables are introduced in the  Information  Principle (“Zipf's Law from a Fisher variational-principle”, http://arxiv.org/abs/0908.0501).Confirms the analogy between the properties of Social Systems  and the Thermodynamics of Gases and Liquids through the “Scale-Free Ideal Gas” (SFIG):Therefore, the Zipf’s Law is  so universal as the Universal Gas Law, as they rise from the same principle, but with different symmetries (“Fisher-information and the thermodynamics of scale-invariant systems”, respectively, http://arxiv.org/abs/0908.0504).
Scientific InnovationSOCIAL THERMODYNAMICSUNIVERSAL LAWSZipf’s Law
Benford’s Law
Dunbar’s Number
Six degrees of separation
“Competitiveness”STh applied to the Network Theory (“Unravelling the size distribution of social groups”, http://arxiv.org/abs/0905.3704)  explains classical” predictions:Prediction of the max. number of contacts (connections)  a human can keep, widely known as the  "Dunbar's number”
Prediction of the min. average distance between any 2 people on the Earth, known as the “Six degrees of Separation”, is a conseq. of Dunbar’s Number. Thanks to Social Thermodynamics, those properties that had been previously detected, only empirically, now have a valid scientific explanation and a model which can be applied to any event.
Scientific InnovationSOCIAL THERMODYNAMICS Social Thermodynamics is not only able to explain classical known properties, but also to predict and detect patterns that have not been discovered yet, such as:
E.g. Prediction of the pattern behind the ‘City-Size Distributions’ and ‘Electoral Results’. The discovery of  a new ‘Universal Scale Rule’ leads to the definition of “Competitiveness”, a new thermodynamic variable that allows to classify and simulate the way people join to create groups of common interests. The way these groups are created and distributed depends totally on the Competitiveness parameterThe pattern behind the real natural events and its results has been now unveiled and explained based on a Universal Law that can be applied to predict other social patterns.Scientific InnovationSOCIAL THERMODYNAMICSUNIVERSAL LAWSZipf’s Law
Benford’s Law
Dunbar’s Number
Six degrees of separation
“Competitiveness”As regularityexists, and the theoretic framework has been created, results can bemodeled and, therefore, predicted !
benefits  of  SOCIAL THERMODYNAMICSappliCATIONto social networks
Applications
Benefits appliedtoorganizations
Solution areas
Whowe areCOMPANY OVERVIEW
Company OverviewAbout SThARSThAR is the developer and world’s leader in the application of Social Thermodynamics Universal Laws to real business needs, which can provide revolutionary solutions, under a whole new scientific methodology.VisionThrough the analysis of network properties and the use of recently discovered physical principles, SThAR will help public and private enterprises  to predict and model social interactions for multiple purposes, delivering an unsuspected powerful tool to explain social events and gain a dramatic competitive advantage:Identifying the network Ebullition Points and, therefore,  the best and most cost-effective Dissemination Strategies(e.g., for viral marketing purposes).Detecting the Achilles’ Heels and most risky areas susceptible to be threatened leading to the weakening/destruction of the network (for churn reduction, detection of mobile viruses spread, etc)Anticipating social changes and predicting future results thanks to a new theoretical  framework, rather than using traditional empirical approaches.
Why is SThAR revolutionary  ?What makes SThAR unique: A disruptive and whole new approach: Versus more than 100 years of conventional empirical based modelsWith a mathematic model that, instead of using well known statistics methods,  explains regularities through physical principles and can predict next ones.Scientific foundation and recognition SThAR scientists  are the creators of the applied Social Thermodynamics .Recognition of the scientific international community.Correlating Operator’s and Environmental NetworksFor a more comprehensive analysis, we can correlate Carrier’s data with  social environment behavior, dramatically enhancing the power and accuracy of the combined prediction results.
Howweworkmethodology
Social ThermodynamicsapplicationMethodologyProject Methodology. 5 Phases:
Methodology1. Data Collection (only 4 required fields)
Methodology2. Network Typification
Methodology3. Environmental Info Correlation
Methodology4. Propagation and Network Behaviour Simulation
Methodology5. Predictive Modeling and Automation
Application of social themodynamicsbusiness case: DRAMATICALLY IMPROVED CHURN ANALYSIS FOR a Mobile operator
Application of Social ThermodynamicsBusiness Case: A Mobile Operator1 single model => 5 applications:Disruptive Churn Analysis Model Advanced Behavioral MarketingClusters and roles identification and behaviors predictionThermodynamicalconditions and environment variable correlationsViral Marketing OptimizationMedia investment optimization  by identifying the opinion makers/ebullition points…New Promotions/Plans/Bundles Acceptance Simulation Virus Quick Spread Prevention5 Solutions for 5 main and totally different issues in a same company applying the same single Theoretical Model
Business Case: A Mobile OperatorMobile Network Recreation (NodeSnowball)FirstLevel Snowboard (Outcomingcalls )FirstLevel Snowboard (SMS)CalldurationdistributionColor: OperatortheuserbelongstoNumber of lines: Number of callsThicknes: Averagecalldurationtothatnumber
Degreecentralitydistribution in a SFIN (Scale-Free Ideal Network)Someexamples of degreetypesBusiness Case: A Mobile OperatorNetwork Modeling. NodesclassificationAnalysis of networkparameters (centrality, degreedistribution, clustering…) allowstoclassifynodes (both, company and competitorsnodesinteractingeachother) and identifythemostinfluential/vulnerable ones. Thatprovidescriticalinformationabouttheirbehavioralpattern (influentialpower, propagationcapacity, and theirrelative position versus theinterestgroups and the global position in thewholenetwork). Thatclassificationisregardlessothersociological variables (sex, ages, race…) thatwillonlybeusedwhendecidinghowtocommunicatethemessages in a Marketing campaign
Business Case: A Mobile OperatorMobile Network. ConnectionsStrengthEvolution of 2 contacts’ connectionsweightsbased on a real mobileoperatorbill.Eachpeakrepresentsanevent. A  highcallfrequencyhelpstokeephighthevalue of thecontactweightdespitethe natural decrease in time.
Business Case: A Mobile OperatorMobile Network. SuscribersConnectionsIllustration of a 1.000 nodesnetworkbased on the SFIN (Scale-Free Ideal Network). Itisclearly visible theGiantcomponent.

SThAR_corporate_presentation_19-09-2009

  • 1.
    therevolutionof SOCIAL THERMODYNAMICSIN BUSINESS APPLICATIONSA new model to predict social changes…
  • 2.
    What these eventshave in common ?Electrical & telephone bills, stock prices, frauds & deaths ratesThe Percolation theory and the nuclear multi-fragmentation The abundances of genes in various organisms and tissuesThe churn distribution in a mobile network operatorThe density distribution of votes in political electionsThe density distribution of urban agglomerationsThe distribution of firm-sizes all over the world The frequency of words in natural languagesThe scientific collaboration networkThe total number of cites of physicsThe Linux packages linksThe Internet traffic…… Are social events determined by universal laws ?
  • 3.
    Unexplained Incredible FactsPhysicistJohn Archibald Wheeler stated that: “All things physical are information-theoretic in origin and this is a participatory universe...”
  • 4.
    Regularity in thewords frequency in natural languages and urban agglomeration was empirically already observed, about 100 years ago: The Zipf’s Law.
  • 5.
    Benford’s Law providesresults which have been found to apply to street addresses, population numbers, lengths of rivers, physical and mathematical constants, and processes described by power laws (which are very common in nature). A little bit of History… background75 years ago, George KingslyZipf (1902-1950), an American linguist and philologist who studied statistical occurrences in different languages, observed incredible regularities, not only in the different languages but in several social distributions. Zipf was Chairman of the German Department and University Lecturer at Harvard University. He worked with Chinese languages and demographics as well. Zipf's law states that while only a few words are used very often, many or most are used rarely, following a proportionality of this type: Pn ~ 1/na, where Pn is the frequency of a word ranked nth and the exponent a is almost 1. This means that the second item occurs approximately 1/2 as often as the first, and the third item 1/3 as often as the first, and so on. The rank vs. frequency distribution of individual incomes in a unified nation approximates this law. Breaks in this "normal curve of income distribution" portend social pressure for change, even revolution. This is demonstrated in his 1941 book, "National Unity and Disunity" in which the break in the curve of income distribution in 1940 in Indonesia predicts revolution there. Revolution began five years later, in 1945..
  • 6.
    Zipf’s LawZipf's law,an empirical law formulated using mathematical statistics, refers to the fact that many types of data studied in the physical and social sciences can be approximated with a Zipfian distribution, one of a family of related discrete power law probability distributions. Up to now, it was not known why Zipf's law holds for most languages. However, it may be partially explained by the statistical analysis of randomly-generated texts.If the natural log of some data are normally distributed, the data follow the log-normal distribution. This distribution is useful when random influences have an effect that is multiplicative rather than additive. .Much of his effort could explain properties of the Internet , distribution of income within nations, and many other collections of data
  • 7.
    Benford’s LawBenford's law,also called the first-digit law, states that in lists of numbers from many (but not all) real-life sources of data, the leading digit is distributed in a specific, non-uniform way. According to this law, the first digit is 1 almost one third of the time, and larger digits occur as the leading digit with lower and lower frequency, to the point where 9 as a first digit occurs less than one time in twenty. This distribution of first digits arises logically whenever a set of values is distributed logarithmically.Real-world measurements are often distributed logarithmically (or equally, the logarithm of the measurements is distributed uniformly). A logarithmic scale bar. Picking a random x position on this number line, roughly 30% of the time the first digit of the number will be 1 (the widest band of each power of ten).
  • 8.
    Benford’s LawThis counter-intuitiveresult has been found to apply to a wide variety of data sets. The results also hold regardless of the base in which the numbers are expressed, although the exact proportions change.It has been argued that Benford's law is a special case of Zipf's law. This special connection between these two laws can be explained by the fact that they both originate from the same scale invariant functional relation from statistical physics and critical phenomena
  • 9.
    Fisher InformationIn mathematicalstatistics and information theory, the Fisher Information (sometimes simply called Information) is the variance of the score. Its role in the asymptotic theory of maximum-likelihood estimation was emphasized by statistician R.A. Fisher The Fisher information is a way of measuring the amount of information that an observable random variable X carries about an unknown parameter θ upon which the likelihood function of θ, L(θ) = f(X;θ), depends. Fisher information is widely used in optimal experimental design. Because of the reciprocity of estimator-variance and Fisher information, minimizing the variance corresponds to maximizing the information.When the linear statistical model has several parameters, the mean of the parameter-estimator is a vector and its variance is a matrix. The inverse matrix of the variance-matrix is called the "information matrix". Using statistical theory, statisticians compress the information-matrix using real-valued summary statistics; being real-valued functions, these "information criteria" can be maximized.
  • 10.
    Dunbar’snumberDunbar's number isa theoretical cognitive limit to the number of people with whom one can maintain stable social relationships. These are relationships in which an individual knows who each person is, and how each person relates to every other person.[1] Proponents assert that numbers larger than this generally require more restricted rules, laws, and enforced norms to maintain a stable, cohesive group. No precise value has been proposed for Dunbar's number, but a commonly cited approximation is 150.Dunbar's number was first proposed by British anthropologist Robin Dunbar, who theorized that "this limit is a direct function of relative neocortex size, and that this in turn limits group size ... the limit imposed by neocortical processing capacity is simply on the number of individuals with whom a stable inter-personal relationship can be maintained." On the periphery, the number also includes past colleagues such as high school friends with whom a person would want to reacquaint themselves if they met again
  • 11.
    Sixdegrees of separationSixdegrees of separation (also referred to as the "Human Web") refers to the idea that, if a person is one step away from each person they know and two steps away from each person who is known by one of the people they know, then everyone is at most six steps away from any other person on Earth. It was popularised by a play written by John Guare.Kevin Bacon Game: The game "Six Degrees of Kevin Bacon" was invented as a play on the concept: the goal is to link any actor to Kevin Bacon through no more than six connections, where two actors are connected if they have appeared in a movie together.
  • 12.
    Confidential and Copyrighted… CAN SOCIAL CHANGES BE PREDICTABLE THROUGH A WHOLE INNOVATIVE MODEL ?
  • 13.
    Background: How itall started ?¡Based on a classical scientific process, a scientist’s curiosity him led to analyze the results of the 2008 Spanish elections and …BackgroundBipartisanshipOtherpartieswithrepresentationPartieswith no representationLn (number of votes)Based on a classical scientific process, a scientist’s curiosity led him to analyze the results of the 2008 Spanish elections and discovered that their logarithmic representation followed , surprisingly, almost a perfect straight line.Ranking
  • 14.
    BackgroundBased on aclassical scientific process, a scientist’s curiosity led him to analyze the results of the 2008 Spanish elections and discovered that their logarithmic representation followed , surprisingly, almost a perfect straight line.
  • 15.
    Such regularitydrove the scientists to search for a pattern behind that behavior, and to explain how people associate to create common interests groups (clusters).Background Expecting this behavior could be exhibited in other real life events and searching for possible analogies, similar results were found in several interesting data collections…
  • 16.
    Like in theresult of the Brazilian elections…BackgroundExpecting this behavior could be exhibited in other real life events and searching for possible analogies, similar results were found in several interesting data collections…
  • 17.
    Like in theresult of the Brazilian elections…
  • 18.
    and in the population distribution in towns in different countries !!…Background: Nothing New Yet! Expecting this behavior could be exhibited in other real life events and searching for possible analogies, similar results were found in several interesting data collections…
  • 19.
    Like in theresult of the Brazilian elections……
  • 20.
    and in the population distribution in towns in different countries !!…In fact, this regularity is what The Zipf’s Law had confirmed for many years.
  • 21.
  • 22.
  • 23.
  • 24.
  • 25.
  • 26.
    Similar regularitieshave been detected in many other social events… BUT …NOBODY HAD BEEN ABLE TO EXPLAIN HOW or WHY THESE REGULARITIES HAPPENED BASED ON SCIENTIFIC PRINCIPLES……AND THERE WAS NEVER A THEORY AVAILABLE TO EXPLAIN IT !!Up to now !! ...
  • 27.
    Scientific InnovationUNIVERSAL SCALERULEAttempting to define a scientifically based framework, which would explain and predict the nature of those events, after trying different models and methodologies, their first conclusion (based on a sound scientific empirical analysis) led to the discovery of a new completely revolutionary scientific concept… … The UNIVERSAL SCALE RULE… !!
  • 28.
    Scientific InnovationUNIVERSAL SCALERULEThanksto the application of this rule, it was proven that the way people form groups of interest (clusters) follows a pattern based on a thermodynamic variable that was named “COMPETITIVENESS” (λ)The pattern behind it all had just been unveiled !!
  • 29.
    Scientific InnovationSOCIAL THERMODYNAMICSIt was the first time that the Information Theory was successfully used to explain reality and the first time that from the “Principle of Minimization of Fisher Information” could be obtained, not only the Relativity, Quantum Mechanics, Classical Electrodynamics, Field Theory, Thermodynamics... but, as well, an innovative theory: “Social Thermodynamics”
  • 30.
  • 31.
  • 32.
  • 33.
    Six degrees ofseparation
  • 34.
    “Competitiveness”Explains both Zipf’sLaw and Benford’s Law: they naturally emerge when the correct symmetry and variables are introduced in the Information Principle (“Zipf's Law from a Fisher variational-principle”, http://arxiv.org/abs/0908.0501).Confirms the analogy between the properties of Social Systems and the Thermodynamics of Gases and Liquids through the “Scale-Free Ideal Gas” (SFIG):Therefore, the Zipf’s Law is so universal as the Universal Gas Law, as they rise from the same principle, but with different symmetries (“Fisher-information and the thermodynamics of scale-invariant systems”, respectively, http://arxiv.org/abs/0908.0504).
  • 35.
  • 36.
  • 37.
  • 38.
    Six degrees ofseparation
  • 39.
    “Competitiveness”STh applied tothe Network Theory (“Unravelling the size distribution of social groups”, http://arxiv.org/abs/0905.3704) explains classical” predictions:Prediction of the max. number of contacts (connections) a human can keep, widely known as the "Dunbar's number”
  • 40.
    Prediction of themin. average distance between any 2 people on the Earth, known as the “Six degrees of Separation”, is a conseq. of Dunbar’s Number. Thanks to Social Thermodynamics, those properties that had been previously detected, only empirically, now have a valid scientific explanation and a model which can be applied to any event.
  • 41.
    Scientific InnovationSOCIAL THERMODYNAMICSSocial Thermodynamics is not only able to explain classical known properties, but also to predict and detect patterns that have not been discovered yet, such as:
  • 42.
    E.g. Prediction ofthe pattern behind the ‘City-Size Distributions’ and ‘Electoral Results’. The discovery of a new ‘Universal Scale Rule’ leads to the definition of “Competitiveness”, a new thermodynamic variable that allows to classify and simulate the way people join to create groups of common interests. The way these groups are created and distributed depends totally on the Competitiveness parameterThe pattern behind the real natural events and its results has been now unveiled and explained based on a Universal Law that can be applied to predict other social patterns.Scientific InnovationSOCIAL THERMODYNAMICSUNIVERSAL LAWSZipf’s Law
  • 43.
  • 44.
  • 45.
    Six degrees ofseparation
  • 46.
    “Competitiveness”As regularityexists, andthe theoretic framework has been created, results can bemodeled and, therefore, predicted !
  • 47.
    benefits of SOCIAL THERMODYNAMICSappliCATIONto social networks
  • 48.
  • 49.
  • 50.
  • 51.
  • 52.
    Company OverviewAbout SThARSThARis the developer and world’s leader in the application of Social Thermodynamics Universal Laws to real business needs, which can provide revolutionary solutions, under a whole new scientific methodology.VisionThrough the analysis of network properties and the use of recently discovered physical principles, SThAR will help public and private enterprises to predict and model social interactions for multiple purposes, delivering an unsuspected powerful tool to explain social events and gain a dramatic competitive advantage:Identifying the network Ebullition Points and, therefore, the best and most cost-effective Dissemination Strategies(e.g., for viral marketing purposes).Detecting the Achilles’ Heels and most risky areas susceptible to be threatened leading to the weakening/destruction of the network (for churn reduction, detection of mobile viruses spread, etc)Anticipating social changes and predicting future results thanks to a new theoretical framework, rather than using traditional empirical approaches.
  • 53.
    Why is SThARrevolutionary ?What makes SThAR unique: A disruptive and whole new approach: Versus more than 100 years of conventional empirical based modelsWith a mathematic model that, instead of using well known statistics methods, explains regularities through physical principles and can predict next ones.Scientific foundation and recognition SThAR scientists are the creators of the applied Social Thermodynamics .Recognition of the scientific international community.Correlating Operator’s and Environmental NetworksFor a more comprehensive analysis, we can correlate Carrier’s data with social environment behavior, dramatically enhancing the power and accuracy of the combined prediction results.
  • 54.
  • 55.
  • 56.
    Methodology1. Data Collection(only 4 required fields)
  • 57.
  • 58.
  • 59.
    Methodology4. Propagation andNetwork Behaviour Simulation
  • 60.
  • 61.
    Application of socialthemodynamicsbusiness case: DRAMATICALLY IMPROVED CHURN ANALYSIS FOR a Mobile operator
  • 62.
    Application of SocialThermodynamicsBusiness Case: A Mobile Operator1 single model => 5 applications:Disruptive Churn Analysis Model Advanced Behavioral MarketingClusters and roles identification and behaviors predictionThermodynamicalconditions and environment variable correlationsViral Marketing OptimizationMedia investment optimization by identifying the opinion makers/ebullition points…New Promotions/Plans/Bundles Acceptance Simulation Virus Quick Spread Prevention5 Solutions for 5 main and totally different issues in a same company applying the same single Theoretical Model
  • 63.
    Business Case: AMobile OperatorMobile Network Recreation (NodeSnowball)FirstLevel Snowboard (Outcomingcalls )FirstLevel Snowboard (SMS)CalldurationdistributionColor: OperatortheuserbelongstoNumber of lines: Number of callsThicknes: Averagecalldurationtothatnumber
  • 64.
    Degreecentralitydistribution in aSFIN (Scale-Free Ideal Network)Someexamples of degreetypesBusiness Case: A Mobile OperatorNetwork Modeling. NodesclassificationAnalysis of networkparameters (centrality, degreedistribution, clustering…) allowstoclassifynodes (both, company and competitorsnodesinteractingeachother) and identifythemostinfluential/vulnerable ones. Thatprovidescriticalinformationabouttheirbehavioralpattern (influentialpower, propagationcapacity, and theirrelative position versus theinterestgroups and the global position in thewholenetwork). Thatclassificationisregardlessothersociological variables (sex, ages, race…) thatwillonlybeusedwhendecidinghowtocommunicatethemessages in a Marketing campaign
  • 65.
    Business Case: AMobile OperatorMobile Network. ConnectionsStrengthEvolution of 2 contacts’ connectionsweightsbased on a real mobileoperatorbill.Eachpeakrepresentsanevent. A highcallfrequencyhelpstokeephighthevalue of thecontactweightdespitethe natural decrease in time.
  • 66.
    Business Case: AMobile OperatorMobile Network. SuscribersConnectionsIllustration of a 1.000 nodesnetworkbased on the SFIN (Scale-Free Ideal Network). Itisclearly visible theGiantcomponent.
  • 67.
    Business Case: AMobile OperatorClustersidentificationThemodulationprocessallowstoidentifycommoninterestgroups , associatedifferentnodesintoclusters, and hierarchically, clusteresintosuperclusters, based on local interactionpatterns, simplyfingnetworkanalysis at clusterslevelsinstead of nodeslevel.
  • 68.
    Business Case: AMobile OperatorCorrelationwithenvironment variablesThermodynamicconditionsidentificationThanksto Social ThermodynamicsTheory, weknownowthatthesizedistributions of thesegroupsdepends on a “Competitiveness” (λ) variable that defines thewayhumansformcommoninterestgroups (e.g.: if a givensocietygroups in manysmallclustersor in a fewbigones, etc)Thevalue of λ , representative of every social group, can beobtainedfrom a number of availablesources (publicdatabases, citiessizedistribution, electoral results, firmssizedistribution…)Thatnumber(λ) has a definitiveinfluence on thebehavior of theopiniontransmissionflows in a social network, as peopleconnections are thewaytheinformationgoesby.Red: Empirical DataBlack: Social ThermodynamicsPrediction
  • 69.
    Business Case: AMobile OperatorDramaticallyimprovingchurndetectionratesWhileexistingChurnpredictivemodelshaveanaccuracy of no more than a 30%, the Social Thermodynamicsbasedmethodologymaydramaticallyincreasethis ratio.
  • 70.
    As anexample, seethelevelof accuracyobtainedbythe Social ThermodynamicsMatematicalmodel (black curve) comparedtoreality (red curve) vs otherstatiscalmodels (seegreen curve)Business Case: A Mobile OperatorChurnAnalysis and ControlThermodynamicalanalogy: CHURN = PHASE TRANSITIONA churnermovingfromonecompanyto a competitor can becomparedwith a watermoleculedroppingoutfrom ice tobecomeliquid (melting).
  • 71.
    Depending on localthermodynamicalconditions (temperature, pressure, density…) someareas are more sensitivetophasechangesthanothers.
  • 72.
    Social ThermodynamicsTheoryprovidesthe socialequivalentframeworktotheclassicalThermodynamics, makingpossibletoanticipatetheSuscriber’sChurnSensitivitywiththesameaccuracythat a phasetransition can bepredicted in theCondensedMatterPhysics, usinganalgorithmbased on thelast Montecarlo developmentsforStatiscalPhysics.Business Case: A Mobile OperatorChurnAnalysis and ControlThermodynamicalconditionsThechurnprocessorphasetransitiondepends on a new thermodynamical variable (εo) whosevalue can beobtainedfrompubliceconomical data, as itkeepsrelationshipwiththe “ConsumptionTemperature”
  • 73.
    It determines, inonesidethePhasechangeprobabilitydistributionwhereε1isanspecificsystemvalue and εo isanindicator of thecost/saving as a result of thetransition.
  • 74.
    In theotherside, the“Economicaltemperature” allowsto describe, thankstothe Montecarlo method, spontaneoustransitions and massiveacquisitions/lost of customersdueto new promotions/offers.Business Case: A Mobile OperatorChurnAnalysis and ControlPotentialChurnersIdentification:The local descriptionprovidesforevery single nodetheir social thermodynamical status regardingphasetransition; notonlyformembers in theneworkbutfromcompetitor’sclients as well, as theyinteractwiththefirstones.
  • 75.
    Thus, thealgorithmallowstofindout inthenetworktheweakestareas and thoseoneswiththehighestgrowthpotential, tooptimizeinvestment in churnprotection and new customersacquisition, protecting/increasingoperator’scustomer base
  • 76.
    In addition, withthismodelitispossibletodetectthosenodesthatcan start a chainreaction and predicttheeffects of a phasetransition in thenetworkclustersgenerated, forexample, by a competitiveoffer, selectingtheareaswhereitwillbe more effective. Business Case: A Mobile OperatorChurnAnalysis and ControlPotentialChurnersIdentification:The local descriptionprovidesforevery single nodetheir social thermodynamical status regardingphasetransition; notonlyformembers in theneworkbutfromcompetitor’sclients as well, as theyinteractwiththefirstones.
  • 77.
    Thus, thealgorithmallowstofindout inthenetworktheweakestareas and thoseoneswiththehighestgrowthpotential, tooptimizeinvestment in churnprotection and new customersacquisition, protecting/increasingoperator’scustomer base
  • 78.
    In addition, withthismodelitispossibletodetectthosenodesthatcan start a chainreaction and predicttheeffects of a phasetransition in thenetworkclustersgenerated, forexample, by a competitiveoffer, selectingtheareaswhereitwillbe more effective. Churn Analysis:SThAR approach vs existing methodsExisting models are always Statistics and based on 2 approaches Usage pattern based: more complex and expensive, but more accurateBilling: cost-effective, lower accuracyLimited accuracyBelow 30% of accuracy in prediction (70% of churneres are not detected)It is noted that amongst 30% customers, many of them will leave whatever actions telco takes. So most customers who are likely to defect will be gone!Need to learn (neuronal learning) and be fed with many inputsLook at themselvesIn addition, we can provide a dynamic model including predictions about the health of the Competitors.We don’t use Statistics to analyze empirically the PAST, but LAWS to predict the FUTURE
  • 79.
    Business Case: AMobile OperatorThePower of PredictingMktg.EffectivenessNew Promotions/Plans/BundlesAcceptanceSimulationWhilethe “EconomicalTemperature” is a global variable, depending on the general economical status, thespecificε1is a local valuethatCAN BE MANIPULATED through Marketing Campaigns.
  • 80.
    FollowingtheequivalencewithclassicalThermodynamics, ε0wouldrepresenttheaveragetemperature ina room, whileε1wouldrepresenttheeffect of turning on an oven or a refrigerator, i.e.the local manipulation of thetemperature.
  • 81.
    “Social temperature” canbemodifiedand theresult of thatmodification can bePREDICTEDthanksto Social Thermodynamics
  • 82.
    Thosepredictions can beusedfora unlimitednumber of marketing simulations :testingthebestCallrates plan, Flat fees, Bundles, Promotions…., havinganunrivalled and unprecedentedtooltogain a definitivemarketcompetitiveadvantage.INFECTED NETWORKFINAL STATUSINITIAL EBULLITION POINTSBusiness Case: A Mobile OperatorAttacks and RareEventsEarlyDetectionReal AttackDetectionThepatternfollowedbyan SMS virus in a massiveattack (e.g.) sendingautonomouslymessagestocontactslists, willsignificativelydifferfromthe usual humanpatterns, allowingtoidentifysuspiciousbehaviors. Thefollow-up of the “Tsunami’sfront” whenearlydetectedwillallowtoidentifytheepidemyfocus, obtaintheproperties of theinfectiondissemination and predictitsevolutiontopreventormitigateitRareevents (Fastdisseminationmessages)Similar behaviour (though of a totallydifferentnature) isobserved in thefastdissemination of news/rumours/messages in very short periods of time (e.g.Xmas SMS, “pass-itnow” messages…). Itisimportanttodifferentiatethedifferenttypesformanypurposes:Detect and avoid, ifnecessary, the use of fraudulentmessages (for legal compliance)
  • 83.
  • 84.
    Avoidlines/networksaturation in veryshorts periods of time througresourcesbalancing.Example: Virus propagation simulationBusiness Case: A Mobile OperatorVirus infectionanalysisFraction of networkinfectedafter 10 epidemiesrandomlygenerated . Someepidemiesdon`tprogresswhileotherextendquicklythroughoutthenetwork.Some of them don ‘t presentanyinitialsymptombutsuddenlystart a wide spread of theinfection.Velocity of infection. Number of infectednodes vs time. Generally, epidemiesgrowexponentiallyuntil a maximumlevel of infection and thendecrease.
  • 85.
    Business Case: AMobile OperatorVirus infectionanalysisSomestartingpoints can wronglybeconsidered as notdangerous, butthescenario can drasticallychangeifsensitivenodes are reached, and theprocessbecome a massiveattack. Generallythenumber of infectednodesgrowsgeometrically in earlystagestoslowdownwhen a saturationpercentage of infectednodesisreached.Fraction of networkinfectedin 10 differentsimulationsTheprogress of theepidemy (contagionpotential) throughthenetworkwillhighlydepend on theinitialfocus(“source of fire”)
  • 86.
    Nodes classification bytheir risk of contagionBusiness Case: A Mobile OperatorVirus propagationsimulationThanksto virus spread simulationswe can:Obtainthedisseminationpatterns
  • 87.
    Classify nodes,i.e. dentify those users susceptible to accelerate the process if they get infected (most contagious) and, therefore…
  • 88.
    Designprevention/defenseplans.Epidemyevolutionin time (t= 1, 3, 5 & 7)Red : InfectednodesGreen: Notinfectednodes
  • 89.
    Numberof nodesinfectedin thenetwork(totalnodes: 1.000) vs Time based on theprobaility of Infection (p) Fractionof Network finallyinfectedafterthe Virus spread, based on theprobability of infection (p) Business Case: A Mobile OperatorVirus infectionanalysisToclassifynodesbyrisk of contagion, a largenumber of disseminationprocesses are simulatedvaryingtheprobability of infection. Depending on the time neededtoreachsaturation and the final fraction of networkinfected a value of infectionpowerisassigned, representingtheircapacitytogenerate and/oraccelerateepidemies.
  • 90.
    Business Case: AMobile OperatorVirus infectionanalysisRecreationof theinfectedcomponentand thesavedonesafterthe Virus spread for p = 0,3Graphicalreproduction of thenetworkshowingthefirst 10 levels of infectednodes, fromtheinitialone.
  • 91.
    ASThROAutomated Socio ThermodynamicsResearch OperativeSThAR Marketing System, is a powerfulall-in-one marketing solutionthatprovidesto Marketing professionalsallthetoolstocreate, plan, launch, track and automatedirect marketing campaignsincluding and advanced Content Manager System (CMS). Based on theinformationobtainedfromthepreviousnetworkanalysis, modelling and predictivesimulations, itallowstoexecute , track and control different online marketing actions and generatethecorrespondingreportstoverifythesuccess of marketing campaigns , analyzedeviations and helptotakecorrectivedecisions .
  • 92.
    ASThROFeatures (I)SubscribersTrackerYouwillknowallyoursubscribers’ actionsthroughsent e-mail and web siteCampaign ManagerYou can define and planify online marketing campaignsfortargettedemailing. Itincludesanapprovalworkflowtool, preliminar emails preview, sendscheduler…  Suscribers ManagerYou can import, export and createautomaticallysuscriberslists, and add (OPT-in) oreliminate (OPT-out) customers at one-click SegmentedSuscribersListYou can manageyoursuscribersbased on segmentationpredefinedcriteria, mergedifferentlistsintoone, managebyusersorbyusers’ profiles , etc.
  • 93.
    ASThROFeatures (II)Events andResponse ManagementYou can control alltheeventsrelatedtoanydirect marketing campaign: sentmessages, readmessages, bounced/failedmessages… and analyze at oneclickthesuscriberhistory , and have a granular control.  Real Time RedemptionAnalysisYou can analyzetheresults of yourcampaigns in real-time, allowingtoverifytheeffectiveness of direct marketing promotions in launch time toquicklydetectdeviations and takecorrectiveactions.On-line Analysis of Off-Line Campaigns  You can analysethesuccess of off-line marketing activitiesbygeography, by media, byadvertisingsupports (TV, press, radio…) throughtheinmediate off-line to on-line traslation.  IntegrationwithClients/ExternalCRMs You can exporttheresults of theCampaignsAnalyzerto Excel and otherformatstobeused/integrated in externalCRMs.
  • 94.
    ASThROFeatures (III)ClientProfilesGenerator Automatic +Manual indicatorsAdvancedsuscriberssearch, byanyfield/list/indicatorPossibilitytoadd new indicatorstopreexistingsuscribers/clustersPossibilityto define individual preferencesregardingdifferentconcepts: type of message, contactfrequency, language, email format…  Business OportunitiesDesignerYou can createyourownbusinessindicatorstogenerate new oppotunitiesalerts.  Advanced Email DesignerYou can use thepredefinedtemplates and designsor use externalones. ItallowstomanageDocuments & Imagestostore in central servers allthecomponentsincluded in emails.  AdvancedNewslettersDesignerYou can design, applyormodifyexistingtemplatesforyourperiodical on-line marketing communications.
  • 95.
    Business Case: AMobile OperatorTheDefinitive MarketingWeapon
  • 96.
    For more information:info@sthar.comWhat if reality was predictable ?Thank s foryourattentionquestions ?www.sthar.com

Editor's Notes

  • #3 These findings allow one to conjecture that this behavior reflects a second class of universality. What all these disparate systems have in common is the lack of a characteristic size, length or frequency for the observable under scrutiny, which makes them scale-invariant
  • #33 nuestro valor añadido:- puesto que tenemos una teoría termodinámica, podemos completar los datos de la red telefónica con una predicción de la red social, que permite incluir otros canales de comunicación para cuando se simulen los flujos de opinión en la sociedad. - este tipo de predicción les puede interesar no sólo para simular la difusión de opinión, si no para tener una estimación de la salud de la red de las otras compañías completando los datos que se obtengan de las llamadas a usuarios de fuera de la red (lo que hablábamos el otro día Ricardo).- por otro lado, haciendo un seguimiento de la evolución de los grupos de interés dentro de la red, podemos determinar sus condiciones termodinámicas (su ecuación de estado) y predecir si va a derretirse o si se está haciendo más sólido (si va a cambiar de estado), y dar una probabilidad de 'melting'.- y además ofrecemos todo lo que hoy en día ya se conocía sobre redes complejas, of course!
  • #37 Social Network AnalyisisProvides a set of methodologies and formulas for calculating a variety of criteria that map and measure the links between things. Using Social Network Analysis, you can get answers to questions like:How highly connected is an entity within a network?What is an entity's overall importance in a network?How central is an entity within a network?How does information flow within a network?
  • #43 Estructura1.1. Reconstrucción de la red1.1.1. La factura de un subscriptorCon los datos de una factura de teléfono —origen, destino, fecha y duración— es posiblereconstruir el diagrama de snowball de primer nivel (nombre y dirección no son necesarios,pudiendo mantener la privacidad de los usuarios):Figura 1. Snowball de primer nivel de las llamadas salientes (izquierda) y SMSs (derechaarriba) obtenido con los datos de una factura de teléfono real. La distribución de la duración delas llamadas también es mostrada (derecha abajo).Con el número de llamadas y la duración se mide la fuerza de una conexión, cuyo valorevoluciona en el tiempo en función de la frecuencia de las llamadas. La estimación de ladependencia temporal tras cada evento responde a un mecanismo teórico libre de escalaajustado a medidas empíricas de comportamiento humano (J. Candia et al, J. Phys. A41 (2008) 224015).El color indica el operador del número al que llama #1, el número de líneas es las veces que ha llamado, y el grosor indica la duración media de las llamadas a ese número.
  • #44 RolesEstudiamos la distribución de grado (número de conexiones por nodo), la correlaciónde grados, la centralidad y el clustering para clasificar a los nodos por su papel dentro dela red, identificando los puntos más influyentes o los más vulnerables, tanto de los nodosde la propia compañía como los de las otras compañías que interaccionan con ésta.La clasificación de nodos se hace por tanto según la influencia y la posición localrespecto a los grupos de interés y global respecto a la red. Es decir, del mismo modo que laidentificación de los clusters, la clasificación se realiza según un patrón de comportamientocon independencia de edad, sexo, nacionalidad, etc. que sólo tendrán relevancia a la horade enfocar el mensaje que se le desee transmitir en una campaña de marketing.
  • #45 Cada vez que se produce un evento (llamada o mensaje) la conexiónse refuerza pero decae en el tiempo como (t + td)−1 donde td depende de la duraciónde la llamada, hasta llegar a un tiempo característico T (seis semanas) en el que decaeexponencialmente:w(t) =1Xi=1exp−t−tiTt − ti + tdi,donde ti son los tiempos en los que sucedió cada evento, siendo i = 1 el último en acontecer.2
  • #46 Conectando suscriptoresCorrelacionando los datos de todos los usuarios podemos encontrar los patrones dela comunicación humana. A partir de los datos reconstruimos dos tipos de red, una redglobal (non-mutual network) donde se consideran todos los contactos, y la red mutua(mutual network), donde sólo se consideran contactos bidireccionales (JP Onnela et al,New J. Phys. 9 (2007) 179). Filtramos de este modo call-centers y en general rare-events,dejando sólo aquellas conexiones que responden a un contacto cotidiano mutuo. En estepunto identificamos el Giantcomponent y la estructura de la red.Figura
  • #47 Identificación de grupos de interés comúnIdentificamos los grupos de interés común mediante modulación, agrupando a los nodosen cúmulos (clusters) en función del patrón de interacción local. Este proceso puede aplicarseen varios niveles haciendo cúmulos de cúmulos para obtener la estructura jerárquicade la red (V.D. Blondel, et al., J. Stat. Mech., (2008) 10008, www.lambiotte.be), y facilitarel trabajo de toma de decisiones al permitir un análisis global de la estructura.Figura 4. El Proceso de modulación ayuda a identificar los clusters y a simplificar la red alpermitir analizarla a nivel de interacción de grupos en lugar de personas.Por tanto, los grupos no se definen siguiendo parámetros clásicos como edad, sexo,nacionalidad, etc, si no por la actividad y el modo de interacción interna y externa. Detodos modos es de esperar que exista cierta correlación entre los grupos y estas variables.
  • #48 Determinación de las condiciones termodinámicas y correlación con elentornoGracias a la Social ThermodynamicsTheory sabemos que la distribución de tamaños deesos grupos depende de una variable termodinámica que llamamos competitividad (). Elvalor de esta variable determina el modo en el que los humanos formamos grupos de interéscomún. Define por ejemplo si la sociedad está diseminada en numerosos pequeños gruposo se concentra en unos pocos grupos grandes, determinando la distribución de tamaños.El valor de esta variable puede conocerse utilizando bases de datos públicas, pues puededeterminarse a partir de la distribución del tamaño de las ciudades, resultados electoraleso el tamaño de las empresas por número de empleados.Figura 5. Izquierda: Distribución de la población de los municipios en las provincias de (a)Girona, (b) Bizkaia, (c) Castelló, (d) Cuenca, (e)Granada, y (f) población de las capitalesespañolas. Puntos rojos: datos empíricos, línea negra: predicción con la Social Thermodynamics.Derecha: Predicción de la provincia de Granada de la Social Thermodynamics (línea negra)comparado con otros modelos (triángulos verdes).El comportamiento de los flujos de opinión dentro de la sociedad dependen fuertementede la competitividad, pues los grupos de personas representan el medio por donde fluye lainformación.
  • #49 Determinación de las condiciones termodinámicas y correlación con elentornoGracias a la Social ThermodynamicsTheory sabemos que la distribución de tamaños deesos grupos depende de una variable termodinámica que llamamos competitividad (). Elvalor de esta variable determina el modo en el que los humanos formamos grupos de interéscomún. Define por ejemplo si la sociedad está diseminada en numerosos pequeños gruposo se concentra en unos pocos grupos grandes, determinando la distribución de tamaños.El valor de esta variable puede conocerse utilizando bases de datos públicas, pues puededeterminarse a partir de la distribución del tamaño de las ciudades, resultados electoraleso el tamaño de las empresas por número de empleados.Figura 5. Izquierda: Distribución de la población de los municipios en las provincias de (a)Girona, (b) Bizkaia, (c) Castelló, (d) Cuenca, (e)Granada, y (f) población de las capitalesespañolas. Puntos rojos: datos empíricos, línea negra: predicción con la Social Thermodynamics.Derecha: Predicción de la provincia de Granada de la Social Thermodynamics (línea negra)comparado con otros modelos (triángulos verdes).El comportamiento de los flujos de opinión dentro de la sociedad dependen fuertementede la competitividad, pues los grupos de personas representan el medio por donde fluye lainformación.
  • #50 Transiciones de fase locales (churn)Analogía con la termodinámicaGracias a la analogía con la termodinámica, el churn puede describirse como una transición de fase, donde un usuario cambiando de compañía es como una molécula de agua desprendiéndose del hielo para formar parte del líquido. Según las condiciones termodinámicaslocales (temperatura, presión o densidad), una región puede ser más susceptible que otra de cambiar de faseHemos desarrollado, dentro del marco de la Social ThermodynamicsTheory, el equivalentesocial de éstos fenómenos. La teoría nos permite predecir la susceptibilidad de unsubscriptor a cambiar de compañía con la misma precisión que que se conoce una transiciónde fase en la física de la materia condensada. El algoritmo se fundamenta en la últimastécnicas de Montecarlo desarrolladas para la física estadística.
  • #51 Transiciones de fase locales (churn)Condiciones termodinámicasEl proceso depende de una nueva variable termodinámica εo cuyo valor puede medirsea partir de datos económicos públicos, pues juega el papel de “temperatura de consumo”.Determina, por un lado, la distribución de probabilidad de cambiar de fasedonde ε1 es un valor de referencia propio del sistema y εo es un indicador del coste odel ahorro producido en la transición. Por otro lado, la temperatura económica permitedescribir, gracias al método de Montecarlo, las transiciones espontáneas y las bajas o altasal servicio en masa producidas por nuevas ofertas.
  • #52 Transiciones de fase locales (churn)Identificación de los nodos susceptibles de cambiar de faseLa descripción es local, permitiendo identificar nodo a nodo su estado termodinámicorespecto a la transición de fase, tanto en miembros de la red como en los miembros de lasotras redes que interaccionan con la propia. El algoritmo permite localizar las zonas de lared que puedan desprenderse o las zonas donde existe una mayor facilidad de crecimiento.Obtenemos una predicción de los efectos de la transición a los grupos de la red, identificandoqué nodo puede generar una reacción en cadena.La interacción con las otras compañías y la estimación de la estructura de sus redespermite predecir el efecto de una campaña en el churn, y seleccionar las zonas donde lacampaña tendrá mayor efecto.
  • #53 Transiciones de fase locales (churn)Identificación de los nodos susceptibles de cambiar de faseLa descripción es local, permitiendo identificar nodo a nodo su estado termodinámicorespecto a la transición de fase, tanto en miembros de la red como en los miembros de lasotras redes que interaccionan con la propia. El algoritmo permite localizar las zonas de lared que puedan desprenderse o las zonas donde existe una mayor facilidad de crecimiento.Obtenemos una predicción de los efectos de la transición a los grupos de la red, identificandoqué nodo puede generar una reacción en cadena.La interacción con las otras compañías y la estimación de la estructura de sus redespermite predecir el efecto de una campaña en el churn, y seleccionar las zonas donde lacampaña tendrá mayor efecto.
  • #54 nuestro valor añadido:- puesto que tenemos una teoría termodinámica, podemos completar los datos de la red telefónica con una predicción de la red social, que permite incluir otros canales de comunicación para cuando se simulen los flujos de opinión en la sociedad. - este tipo de predicción les puede interesar no sólo para simular la difusión de opinión, si no para tener una estimación de la salud de la red de las otras compañías completando los datos que se obtengan de las llamadas a usuarios de fuera de la red (lo que hablábamos el otro día Ricardo).- por otro lado, haciendo un seguimiento de la evolución de los grupos de interés dentro de la red, podemos determinar sus condiciones termodinámicas (su ecuación de estado) y predecir si va a derretirse o si se está haciendo más sólido (si va a cambiar de estado), y dar una probabilidad de 'melting'.- y además ofrecemos todo lo que hoy en día ya se conocía sobre redes complejas, ¡por supuesto!
  • #55 Manipulación local de la temperatura de consumoMientras que la temperatura económica es una variable global que depende del estadoeconómico general, el valor de referencia "1 es local y puede ser manipulado mediantecampañas de marketing. Siguiendo la equivalencia con la termodinámica, "0 representaríala temperatura media de la habitación mientras que "1 representaría el efecto de un encendedoro una nevera, es decir, la manipulación local de la temperatura. La temperaturalocal real puede modificarse, y el efecto predecirse gracias a la Social Thermodynamics.Figura 10. Red con tres operadoras (rojas, verdes y amarillas).Planificación de ofertas, planes tarifarios, nuevos bundles…Gracias a la simulación ahora es posible poner a prueba el efecto de un cambio en lastarifas en el churn antes de hacerlo efectivo. Las predicciones pueden utilizarse para eldesarrollo y optimización de la tarifa más efectiva en función de los usuarios ganados y elbeneficio neto.
  • #56 Detección de ataques y Simulación de “tsunamis”Detección de un ataque realEl patrón seguido por el virus al enviar mensajes ed forma autónoma a la lista de contactosdiferirá del patrón habitual de la comunicación humana, lo que permitirá identificarque se está produciendo el ataque. El seguimiento del frente —o del tsunami— de mensajesnos dará las propiedades de la expansión, permitiendo identificar los focos de la epidemiay predecir su evolución con fin de evitarlo.Eventos raros (rareevents)Es importante diferenciar la expansión de un virus de la difusión de una noticia real(efecto “pásalo”), o de los mensajes de felicitación en fiestas navideñas. En este último caso,la simulación de difusión puede permitir el diseño de un protocolo de recomendación deuso a los suscriptores con fin de evitar saturación de líneas (aunque al final nadie hará nicaso, y no hace falta teoría para saber eso!).Por otro lado, el análisis de un evento del tipo “pásalo” de carácter fraudulento —con la intención de difundir una noticia falsa, ya sea de carácter político, financiero odifamatorio— permitiría localizar el foco y desmentir el bulo rápidamente.
  • #57 SeguridadAtaques de virusLa aparición en el mercado de los smartphones permitirá que los virus informáticossalten masivamente al mundo móvil. Un virus capaz de difundirse a través de SMSs multimediapuede llegar infectar la red en unas pocas horas. Disponer de un plan de actuaciónserá fundamental en los próximos años.Simulación de ataquesMediante simulaciones de difusión en la red, pueden predecirse los distintos patronesde la expansión del virus y su dependencia con los focos iniciales. Mediante una estimaciónde la estructura de la red del resto de compañías, podemos incluir el efecto de la difusióndel virus dentro y fuera de la red propia.La expansión depende fuertemente del foco y de la estructura de la red, del mismomodo que la expansión de un incendio depende de las características y de la distribuciónde los objetos o flora de la zona. Hoy en día, gracias al conocimiento adquirido sobre ladifusión del fuego, los investigadores son capaces de encontrar el foco o de preparar accionesóptimas para su extinción. La misma estrategia puede ser aplicada en el ataque de un virus.
  • #58 SeguridadAtaques de virusSegún el foco y su entorno, el virus puede pasar de un escenario en el que no llega aexpandirse significativamente al escenario opuesto de contaminar una fracción muy altade la red. Al mismo tiempo, la velocidad de la epidemia varía fuertemente según la localizacióndel foco, y pese a que pueda darse el caso de que en los estadios iniciales notenga una expansión acelerada y se le considere erróneamente no peligroso, el escenariopuede cambiar si alcanza nodos susceptibles de acelerar el proceso. En general, el númerode nodos infectados crece inicialmente de forma geométrica para frenarse posteriormentehasta saturar a un valor final, que constituye el porcentaje total de nodos infectados trasla epidemia.
  • #59 Clasificación de los nodos por su susceptibilidad epidémicaGracias a las simulaciones pueden conocerse los patrones de expansión y preparar planesde prevención, identificando a aquellos usuarios que sean susceptibles de acelerar el procesoen caso de ser infectados. Los nodos son clasificados según su capacidad de infectar la reden el caso de ser foco de infección. Se selecciona el nodo y se inicia un largo númerode procesos de difusión a diferentes probabilidades de infección. En función del tiemponecesitado hasta saturar y la fracción final de la red infectada se le adjudica un valor querepresente su capacidad de generar o acelerar epidemias.
  • #66 Manipulación local de la temperatura de consumoMientras que la temperatura económica es una variable global que depende del estadoeconómico general, el valor de referencia "1 es local y puede ser manipulado mediantecampañas de marketing. Siguiendo la equivalencia con la termodinámica, "0 representaríala temperatura media de la habitación mientras que "1 representaría el efecto de un encendedoro una nevera, es decir, la manipulación local de la temperatura. La temperaturalocal real puede modificarse, y el efecto predecirse gracias a la Social Thermodynamics.Figura 10. Red con tres operadoras (rojas, verdes y amarillas).Planificación de ofertas, planes tarifarios, nuevos bundles…Gracias a la simulación ahora es posible poner a prueba el efecto de un cambio en lastarifas en el churn antes de hacerlo efectivo. Las predicciones pueden utilizarse para eldesarrollo y optimización de la tarifa más efectiva en función de los usuarios ganados y elbeneficio neto.