Tag Archives: Data Models

The My Face Value “Tout Free” Guarantee

My Face Value is preparing for launch on 31st December 2017. To keep up to date with the latest news follow us on Facebook and Twitter

The My Face Value ability to tackle the problem of touts using our community is key to  earning and retaining the trust of the My Face Value community. The algorithms that My Face Value have developed to solve this problem are only one of many unique selling points in the My Face Value promise to genuine fans.

Using Innovative Technology To Beat The Touts

Similar to the auditable Random Number Generator algorithms that our Random Picking Software utilises to ensure fairness & transparency when selecting winners of our competitions & promotions, our approach to Phishing Prevention, Intercept “Man in the Middle” Attacks and our proprietary Automated Tout Detection systems use our own set of proprietary processes and algorithms to keep My Face Value secure and “tout free”.

My Face Value have developed sophisticated mechanisms that protect the data that the My Face Value community entrust us with and prevent the My Face Value community unwittingly assisting touts in their efforts to buy tickets at face value.

Protection from Trolls and Hackers 

My Face Value expects to be the target of concerted campaigns by trolls (on a simplistic level) and hackers (in a sophisticated manner) because My Face Value are dislodging and disrupting a lucrative “street level” business as well as a “respectable” corporate sector who make large amounts of money from ticket touting and price gouging tickets to events.

The first target of these hacks as we see it would be to undermine the trust in the My Face Value community by targeting our community members’ data, in all its forms. But in particular our community members credit card details. Aside from the myriad white-hat hacker tests that we have conducted, our operating systems, applications and network configurations have been comprehensively penetration tested by leaders in the field.

The Safety of Your Data – Security & Encryption 

My Face Value uses security protocols that protect the My Face Value community member from malicious interception attacks. My Face Value use a secure and encrypted connection (HTTPS/SSL) when handling My Face Value community members’ data.

The My Face Value EV SSL certificate offers the highest available levels of trust and authentication to our website. When performing transactions, the green address bar prominently displays our company name and provides highly visual assurance to customers that our site is secure – immediately giving the My Face Value community member the confidence to complete their transaction.

Sensitive Data Storage

For a further level of comfort My Face Value use an external provider with PCI Service Provider Level 1 Certification (the most stringent level of certification) to manage the process of no-hassle security and compliance that meets all PCI-DSS requirements for desktop and mobile transactions [PCI-DSS: The Payment Card Industry Data Security Standard (PCI DSS) is a proprietary information security standard for organisations that handle branded credit cards from the major card schemes including Visa, MasterCard, American Express, Discover, and JCB.]

No sensitive data hits the My Face Value servers. To bolster this counter measure My Face Value have added an extra layer of security in the form of Two-Factor Authentication.

Phantom Community Members / Spam Accounts

But how do My Face Value detect touts posing as allegedly legitimate community members and avoid the scenario where the tout uses the My Face Value community as a source of leads to purchase tickets at face value and then tout.

The My Face Value community, without the measures that we have taken, would be a readily available environment with millions of community members which touts could “raid” for tickets.

The Value of Anonymity

This process is outlined in great detail on our website and on our social media pages. But in short, the answer to preventing the use of My Face Value as a ticket sourcing platform for touts is “anonymity”.

The information posted by My Face Value community members in relation to BUY/SELL/SWAP requests is not visible to the My Face Value community. Rather My Face Value store the data and identify matching BUY requests with SELL offers and SWAP requests with SWAP matches.

The relevant My Face Value Community members are then notified simultaneously by email. The email contains a link and when clicked this link will allocate the ticket on a First-Come-First-Served basis to the first My Face Value community member who secures the ticket by making the required payment.

The SELLER / SWAPPERS are then requested to send the ticket(s) to My Face Value for a counterfeit check and thereafter – assuming no issues relating to payment fraud or counterfeiting arise – My Face Value will post the ticket to the BUYER and pay the SELLER or in the case of SWAPS post the tickets to the respective My Face Value community members.

The process is managed from end-to-end by My Face Value to ensure compliance.

Detecting “Organised Touting” in the My Face Value Community

My Face Value will keep the community tout free. The BUY/SELL/SWAP Process is conducted thru a series of simple menu selections. This process is outlined in detail on our website and on our social media pages. Once completed and in order to SUBMIT the information to the My Face Value databases – the My Face Value community member is requested to LOGIN, if they have not already done so, or REGISTER – if they are not an existing My Face Value community member.

Now the science bit – the steps in the REGISTRATION process provide one level of protection against touting – but not enough. Sweat shops exist and the industry (organised crime element) are well capable of setting up hundreds of identities and email addresses using pre-paid cards in an attempt to circumvent this LOGIN or REGISTER Wall counter measure.

Tout Prevention & Community Compliance 

My Face Value have developed systems to encode expertise for detecting touts, in the form of rules. Employing Big Data Analysis / Data Mining to develop community member behaviour patterns and profiles for matching against a baseline to detect deviations and automatic responses / actions or in certain cases issue automated real time notifications to the  My Face Value Tout Prevention & Community Compliance Team for examination (See Level 1-4 below for details on this process).

The My Face Value Pattern Recognition techniques to detect clusters or patterns of suspicious behaviour are automated to ensure scaleability. Machine learning techniques automatically identify the characteristics of touting. The My Face Value algorithms learn suspicious patterns from samples which are then used later to detect breaches.

My Face Value deploy these detection algorithms on a number of levels using statistical techniques and artificial intelligence:

Level 1: Email addresses used by a community member, contact telephone number provided by a community member, frequency and time of day of logins by a community member, number and type of payment instruments used by a community member, transactions levels (numbers of transactions) by a community member, types of transactions conducted by a community member – BUY/SELL/SWAP;

Level 2: Combining source metadata, platform and device usage, IP address, browser type, geo-location (clustering), proxy spoofing and VPN detection to augment the Level 1 data My Face Value hold on behaviour patterns;

Level 3: Cross referencing My Face Value community member profiles with publicly available information on social media accounts for pattern matching and augmenting the community member risk profiling data to augment the Level 1 and Level 2 data;

Level 4: In the event that all the information points to a positive breach of the My Face Value Community Guidelines then the community member will be blocked. In circumstances where the information points to a possible breach of the My Face Value Community Guidelines then the My Face Value Tout Prevention & Community Compliance Team will request identification and documents to prove that the “member” is not a phantom account AND that the documents supplied to vouch for that assertion are genuine.

The My Face Value “Tout Free” Guarantee

By implementing Behaviour Analytics & Profiling with Context Data the My Face Value Machine-Learning Algorithms ensure a tout free environment. These processes reduce to almost zero the ability for touts to engage in the volume transactions that would make the effort commercially viable or feasible.

Whether dealing with touts as individuals or organised gangs their inability to fool the profiling algorithms and/or comply with the My Face Value escalating requests for proof of identity to determine if a suspicious account is in fact a genuine fan will keep our community tout free.

The My Face Value Tout Prevention & Community Compliance Team

 

Is Kosinski “Tesla” to Nix’s “Marconi” for Big Data Psychographic Profiling?

Data Driven Democracy Where Opinions, Policies or Convictions Don’t Matter Just The Targeted Message on Facebook Dark Posts.

Cambridge Analytica (Steve Bannon, Board Member) owned by SCL (Strategic Communication Laboratories) – the self styled “premier election management agency” – and how they “helped” Trump, Farage, Brexit, Cruz, Ukraine, Nigeria, Nepal & Afghanistan influence outcomes using data modelling and psychographic profiling.

I HAD never heard of Mr. Kosinski until I read an article in Motherboard last week. The incredibly interesting read entitled The Data That Turned the World Upside Down was written by Hannes Grassegger and Mikael Krogerus who work for Das Magazin with additional research by Paul-Olivier Dehaye.

It discusses a series of intersections between the work of Mr. Kosinski, a vaguely sinister guy called Alexander James Ashburner Nix, CEO of Cambridge Analytica (board member Steve “Ahem” Bannon) and a seemingly innocuous chap called (in 2014) Aleksandr Kogan (now quite unbelievable known as Dr. Spectre (seriously)) with associations to a definitely sinister company called SCL, or Strategic Communication Laboratories who describe themselves as “the premier election management agency”.

The main points are this, but I strongly recommend that you read the original article:

  1. Kosinski and fellow student David Stillwell use data from a Facebook application called MyPersonality, that Stilwell developed in 2007, to create models from “personality profile” data acquired from users who opt-in to share their app answers with researchers. Kosinski and Stillwell are both doctoral candidates studying together in Cambridge University at the Psychometrics Centre;
  2. The MyPersonality app is an unexpected hit with millions of people submitting answers;
  3. They find that remarkably reliable deductions could be drawn from simple online actions. For example, men who “liked” the cosmetics brand MAC were slightly more likely to be gay; one of the best indicators for heterosexuality was “liking” Wu-Tang Clan. Followers of Lady Gaga were most probably extroverts, while those who “liked” philosophy tended to be introverts;
  4. In 2012, Kosinski proved that on the basis of an average of 68 Facebook “likes” by a user, it was possible to predict their skin color (with 95 percent accuracy), their sexual orientation (88 percent accuracy), and their affiliation to the Democratic or Republican party (85 percent);
  5. Kosinski continued to work on the models before long, he was able to evaluate a person better than the average work colleague, merely on the basis of ten Facebook “likes.” Seventy “likes” were enough to outdo what a person’s friends knew, 150 what their parents knew, and 300 “likes” what their partner knew. More “likes” could even surpass what a person thought they knew about themselves;
  6. On the day that Kosinski published these findings, he received two phone calls. The threat of a lawsuit and a job offer. Both from Facebook;
  7. Around this time, in early 2014, Kosinski was approached by a young assistant professor in the psychology department called Aleksandr Kogan. He said he was inquiring on behalf of a company that was interested in Kosinski’s method, and wanted to access the MyPersonality database. Kogan wasn’t at liberty to reveal for what purpose; he was bound to secrecy;
  8. Kogan revealed the name of the company he was representing: SCL, or Strategic Communication Laboratories;
  9. Kosinski came to suspect that Kogan and a company that he had formed might have reproduced the Facebook “Likes”-based Big Five measurement tool in order to sell it to this election-influencing firm;
  10. Cambridge Analytica subsequently acted for Farage in the Brexit campaign and Republican Ted Cruz then they were hired by Trump;
  11. Cambridge Analytica buys personal data from a range of different sources, like land registries, automotive data, shopping data, bonus cards, club memberships, what magazines you read, what churches you attend. Nix displays the logos of globally active data brokers like Acxiom and Experian—in the US, almost all personal data is for sale. For example, if you want to know where Jewish women live, you can simply buy this information, phone numbers included. Now Cambridge Analytica aggregates this data with the electoral rolls of the Republican party and online data and calculates a Big Five personality profile. Digital footprints suddenly become real people with fears, needs, interests, and residential addresses;
  12. Trump’s striking inconsistencies, his much-criticized fickleness, and the resulting array of contradictory messages, suddenly turned out to be his great asset: a different message for every voter. The notion that Trump acted like a perfectly opportunistic algorithm following audience reactions is something the mathematician Cathy O’Neil observed in August 2016;
  13. Why did he behave like this?;
  14. “Pretty much every message that Trump put out was data-driven,” Alexander Nix remembers. On the day of the third presidential debate between Trump and Clinton, Trump’s team tested 175,000 different ad variations for his arguments, in order to find the right versions above all via Facebook. The messages differed for the most part only in microscopic details, in order to target the recipients in the optimal psychological way: different headings, colors, captions, with a photo or video. This fine-tuning reaches all the way down to the smallest groups, Nix explained in an interview with us. “We can address villages or apartment blocks in a targeted way. Even individuals.”;
  15. When did having an opinion or a conviction matter in a “data driven” democracy – it certainly did not seem to matter to Trump;
  16. In the Miami district of Little Haiti, for instance, Trump’s campaign provided inhabitants with news about the failure of the Clinton Foundation following the earthquake in Haiti, in order to keep them from voting for Hillary Clinton. This was one of the goals: to keep potential Clinton voters (which include wavering left-wingers, African-Americans, and young women) away from the ballot box, to “suppress” their vote, as one senior campaign official told Bloomberg in the weeks before the election. These “dark posts” – sponsored news-feed-style ads in Facebook timelines that can only be seen by users with specific profiles – seem to have been highly significant in Trump’s election;
  17. In a statement after the German publication of this article, a Cambridge Analytica spokesperson said, “Cambridge Analytica does not use data from Facebook. It has had no dealings with Dr. Michal Kosinski. It does not subcontract research. It does not use the same methodology. Psychographics was hardly used at all. Cambridge Analytica did not engage in efforts to discourage any Americans from casting their vote in the presidential election. Its efforts were solely directed towards increasing the number of voters in the election.”;
  18. Confusingly the Cambridge Analytica website states “Powered by smarter data modeling At Cambridge Analytica we use data modeling and psychographic profiling to grow audiences, identify key influencers, and connect with people in ways that move them to action. Our unique data sets and unparalleled modeling techniques help organizations across America build better relationships with their target audience across all media platforms.”

ENDS