Persona Technology is a real-time unsupervised machine learning algorithm that identifies direct and indirect linkages between transactions. It is designed to detect emerging fraud across Kount’s vast network of online businesses and their transactions. The Persona Score is a measure of the transaction risk generated by Persona Technology.
Identifying a Persona
A Persona is a set of transactions linked by common attributes. Persona is not a static medium; but rather they are created and updated in real-time as transactions are submitted to Kount. Persona Technology is optimized to filter outdated transactions to ensure that a Persona represents current activity limited to the last 14 days.
Calculating Persona Score
In real-time, Kount derives over 200 data elements from a Persona that provide insight into the risk of a transaction. The score is calculated by analyzing these data elements via a proprietary mathematical algorithm. Some of the data elements that can impact the value of the score are as follows:
- Device country location
- Number of unique payment tokens, device IDs, or emails associated to the Persona
- Specific attributes of the physical device from which the order was placed, including language settings, time zone settings, and other user-selected elements
- Payment information
- Network type
The score indicates the risk level for a given transaction based on data linked to other transactions. It ranges from 1-99, with 99 being the riskiest.
Interpreting Persona Score
Transaction risk is the inverse of transaction safety. The Persona Score is a measure of transaction risk ranging from 0 (low risk) to 99 (high risk). Higher Persona Scores indicate higher risk.
The table below provides guidelines for interpreting the Persona Score. These guidelines are based on analysis across Kount’s entire merchant base. Actual results for a merchant can vary depending on unique characteristics of the integration with Kount and the merchant’s business model. Please contact your Client Success Representative for assistance.
Persona Score |
Risk Level |
Description |
0-40 |
Low Risk |
Small Persona, few if any risk factors |
41-70 |
Medium Risk |
Some risk factors present in Persona |
71-99 |
High Risk |
Large Persona and/or significant risk factors |
Persona Orders and Linked Orders
Persona Orders are orders that have been linked together through a comparison of data across the entire Kount network of customers during the 14-day life of the Persona. Only the linked orders from within a customer's website display under the Persona Orders link, and transactions older than two weeks do not display.
Link Analysis displays a 24-month rolling history of all orders linked together from within a single merchant's website.
Differentiating GEOX and Device Location
The GEOX indicator is an ISO Country Code which represents the country with the highest level of known e-commerce risk, as determined by the US State Department, that has been associated with a particular Persona within the last 14 days. The GEOX is not the same as the physical device location, but rather an indication of where the associated Persona has been seen.
The Device Location represents where the device was located when the customer placed their order.
How can an order with a U.S. Billing Address have a GEOX of Another Country?
For each order received and processed by Kount, we evaluate that order to either associate it to a current Persona or to start a new Persona (if no shared information is found). When an order is associated with an existing Persona, Kount will use all of the information available to determine the best risk assessment possible.
During the evaluation process, Kount examines each of the orders linked to the Persona from the past 14 days to identify the risk factors. One of the main risk factors is called the GEOX or Persona Country of Highest Risk. The GEOX is determined by evaluating all of the linked orders to determine all of the different geographies and device locations associated with the order. For example, if we have linked orders together and discovered multiple different devices being used, we'll look at the country locations for all of the devices and select the one which has the highest risk for e-commerce fraud.
So, if an order has a U.S. Billing address, but a GEOX of China or any other country, this is due to Kount associating and linking orders together, and from this linking, identifying the country of greatest risk.
If there are no associated orders for the Persona, then the GEOX value would be based upon a single order and the riskiest country associated with the current order will be displayed. For example, if there was no prior Persona and the billing address is a U.S. address, and Kount determined that the device was located in Canada, then the GEOX value will be displayed as "CA" based on the device being detected in Canada.
ISO Language Codes
Language | Language Description |
AB | Abkhazian |
AA | Afar |
AF | Afrikaans |
NS | Afrikaans |
SQ | Albanian |
AM | Amharic |
AR | Arabic |
HY | Armenian |
AS | Assamese |
AX | Assyrian |
AE | Avestan |
AY | Aymara |
AZ | Azerbaijani |
BM | Bambara |
BA | Bashkir |
EU | Basque |
BN | Bangali |
DZ | Bhutani |
BH | Bihari |
BK | Bikol |
BI | Bislama |
NB | Bokmal |
BS | Bosnian |
BR | Breton |
BG | Bulgarian |
MY | Burmese |
BE | Byelorussian |
KM | Cambodian |
CC | Cantonese |
VC | CapeVerdean |
CA | Catalan |
CB | Cebuano |
CH | Chamorro |
CE | Chechen |
II | Chinese |
ZH | Chinese |
CK | Chuukese |
CV | Chuvash |
KW | Cornish |
CO | Corsican |
HR | Croatian |
CS | Czech |
DA | Danish |
PG | DariAfghanPersian |
DY | Dioula |
NL | Dutch |
EN | English |
EO | Esperanto |
ET | Estonian |
FO | Faroese |
FA | Farsi |
FJ | Fiji |
FI | Finnish |
FL | Flemish |
FR | French |
FY | Frisian |
GL | Galician |
KA | Georgian |
DE | German |
EL | Greek |
KL | Greenlandic |
GN | Guaran |
GU | Gujarati |
HC | HaitianCreole |
HA | Hausa |
HE | Hebrew |
IW | Hebrew |
HZ | Herero |
HL | Hiligaynon |
HI | Hindi |
HO | HiriMotu |
HM | Hmong |
HU | Hungarian |
IB | Iban |
IS | Icelandic |
IL | Ilocano |
ID | Indonesian |
IN | Indonesian |
IA | Interlingua |
IU | Inuktitut |
IK | Inupiak |
GA | IrishGaelic |
IT | Italian |
JA | Japanese |
JW | Javanese |
KN | Kannada |
KS | Kashmiri |
KK | Kazakh |
KI | Kikuyu |
RW | Kinyaruanda |
KY | Kirghiz |
RN | Kirundi |
KV | Komi |
KO | Korean |
KP | Kpelle |
KU | Kurdish |
LO | Lao |
LA | Latin |
LV | Latvian |
LN | Lingala |
LT | Lithuanian |
LB | Luxemburgish |
MK | Macedonian |
MG | Malagasy |
MS | Malay |
ML | Malayalam |
MT | Maltese |
CM | Mandarin |
MA | Maninka |
GV | ManxGaelic |
MI | Maori |
MR | Marathi |
MH | Marshallese |
MO | Moldavian |
MN | Mongolian |
NA | Nauru |
NV | Navajo |
ND | Ndebele |
NR | Ndebele |
NG | Ndonga |
NE | Nepali |
IG | Nigerian |
NI | Nigerian |
NO | Norwegian |
NY | Nyanja |
NN | Nynorsk |
OC | Occitan |
OR | Oriya |
OM | Oromo |
OS | Ossetian |
PI | Pali |
PP | Papiamiento |
PS | Pashto |
PL | Polish |
PT | Portuguese |
PA | Punjabi |
QU | Quechua |
RM | Rhaeto |
RO | Romanian |
RU | Russian |
SE | Sami |
SM | Samoan |
SG | Sangho |
SA | Sanskrit |
SC | Sardinian |
GD | ScotsGaelic |
SR | Serbian |
SH | SerboCroat |
ST | Sesotho |
TN | Setswana |
SN | Shona |
SD | Sindhi |
SI | Sinhalese |
SS | Siswati |
SK | Slovak |
SL | Slovenian |
SO | Somali |
ES | Spanish |
SU | Sudanese |
SW | Swahili |
SV | Swediah |
TL | Tagalog |
TY | Tahitian |
TG | Tajik |
TA | Tamil |
TM | Tamil |
TT | Tatar |
TE | Telugu |
TH | Thai |
BO | Tibetan |
TI | Tigrinya |
TO | Tonga |
TS | Tsonga |
TR | Turkish |
TK | Turkmen |
TW | Twi |
UG | Uigur |
UK | Ukrainian |
UR | Urdu |
UZ | Uzbek |
VI | Vietnamese |
VO | Volapuk |
CY | Welsh |
WO | Wolof |
XH | Xhosa |
JI | Yiddish |
YI | Yiddish |
YO | Yoruba |
ZA | Zhuang |
ZI | Zhuang |
ZU | Zulu |
Comments
0 comments
Article is closed for comments.