FFT-method expert vailidity
How to recognise fake online stores
Why is it difficult to provide decision support for problems of uncertainty?
How to construct a decision tree for a consumer problem - the FFT method of expert feature validity
A. What do you need?
B. How do you proceed?
- Aikman, D., Galesic, M., Gigerenzer, G., Kapadia, S., Katsikopoulos, K. V., Kothiyal, A., ... & Neumann, T. (2014). Taking uncertainty seriously: Simplicity versus complexity in financial regulation. Bank of England Financial Stability Paper, 28.
- Green, L., & Mehr, D. R. (1997). What alters physicians' decisions to admit to the coronary care unit?. Journal of Family Practice, 45(3), 219–226.
- Jablonskis, E., & Czienskowski, U. (2017). Decision trees online. http://www.adaptivetoolbox.net/Library/Trees/TreesHome#/
- Jenny, M. A., Pachur, T., Williams, S. L., Becker, E., & Margraf, J. (2013). Simple rules for detecting depression. Journal of Applied Research in Memory and Cognition, 2(3), 149–157.
- Luan, S., Schooler, L. J., & Gigerenzer, G. (2011). A signal-detection analysis of fast-and-frugal trees. Psychological Review, 118(2), 316.
- Martignon, L., Katsikopoulos, K. V., & Woike, J. K. (2008). Categorization with limited resources: A family of simple heuristics. Journal of Mathematical Psychology, 52(6), 352–361.
Perhaps the following situation seems familiar to you: For weeks you have been looking for a particular pair of sneakers. The manufacturer's website says that the model is sold out. You also cannot find anything on other mail order sites that are familiar to you. But then you come across a retailer, who you have never heard of, but who is offering a photo of exactly that type of shoe you want so badly. In fact, it is even 100 euros cheaper than on manufacturer's site. How lucky you are! Or are you?
Many people fall for the phenomenon of fake online stores. The only goal of these stores is to deprive you of your money. You will never receive the goods - or at least not the type you have ordered. These scam stores are rarely recognizable at first glance. This is also due to the fact that these websites are designed in an increasingly professional way and look like real online stores. With our decision tree you can check whether a website is a potential scam.
When do I need this graphic?
If you are shopping online and are trying out a new online retailer that you presumably found through a Google search, then this decision tree is for you.
You can also check the store in question extensively. However, please note that no text and no checklist is ever perfect. With every additional feature that you check, the risk of an incorrect assessment of the text increases.
Further features are:
- The AGB refers to the legal right of withdrawal of 14 days from online purchase.
- General terms and conditions are available
- While entering your address for the order: does the website at the top of the browser start with "https"?
- Reference to the commercial register with corresponding number starting as follows "HR...". [not "Ust." = "sales tax"]
- A German-language presentation describing the company (retailer) is available.
- Contradiction in content between Internet address and type of product (e.g. shoes at a doctor's office) [NEGATIVE NOTE].
- Capitalization is wrong [NEGATIVE NOTE]
- Negative reports from customers can already be found on the first page with hits if you google the "store name" in quotation marks [NEGATIVE FEATURES].
- Only prepayment options offered as payment method [no payment by invoice, no direct debit] [NEGATIVE NOTE].
Where is the data coming from?
Cases – Which e-stores served as a basis?
255 German-langue online stores were compiled as the basis for training and test data sets. They were researched by experts from the Harding Center of Risk Literacy.
Target assessment – How was the status of scam stores and conventional online retailers determined?
Fake online stores were determined when they were reported as such (verbraucherschutz.de), or seal theft was reported by Trustedshops. For conventional online stores Trustedshops were randomly selected and the 100 top-selling online retaielrs were included.
Potential features – Which features were considered?
Based on various sources (computerbetrug.de, Europol, onlinewarnungen.de, originalo.de, sidnlabs.nl, verbraucherzentrale.de) 35 features were collected, 17 of which were considered as assessable by laypersons in principle.
Selection of features and modelling
The aim of the pre-selection of features was to limit the number of potential features for the prediction model. The feature selection was performed under two aspects: Testability through laypersons and statistical significance.
What is the quality of the data?
The data set was randomly divided into training data sets (two thirds) and test data sets (one third).
The model is of the following quality:
A cross validation of the identified decision tree resulted in the following quality measures: balanced accuracy = 0.91; correct rejection of fake online stores (share of 57% in the test set) with 0.94. This means that 94 of 100 of such scam stores were detected by the decision tree.
The detection of conventional online stores was 0.88.
Potential for development
Empirical evaluation with consumers
• Computerbetrug.de (2017). Vorsicht beim Online-Shopping: So erkennen Sie einen Fake-Shop. Internet https://www.computerbetrug.de/2017/12/betrug-fake-shop-im-internet-erkennen-6562. Letzter Zugriff 25.11.2019.
• Europol (2019). How to detect fraudulent sites selling fakes. Internet
https://www.europol.europa.eu/activities-services/public-awareness-and-prevention-guides/how-to-detect-fraudulent-sites-selling-fakes. Letzter Zugriff 25.11.2019.
• Originalo.de (2019). Fake-Shops erkennen – Die wichtigsten Merkmale. Internet
https://www.originalo.de/info/fake-shops-sicher-erkennen. Letzter Zugriff 25.11.2019.
• Phillips, N. D., Neth, H., Woike, J. K., & Gaissmaier, W. (2017). FFTrees: A toolbox to create, visualize, and evaluate fast-and-frugal decision trees. Judgment and Decision making, 12(4), 344-368.
• van Spaandonk, C., Lastdrager, E., & Lansing, E. (2018). Fake webshops on .nl and .dk. Präsentation. https://www.sidnlabs.nl/downloads/presentations/jamboree2018-fakewebshops.pdf. Letzter Zugriff 15.03.2019.
• Verbraucherzentrale.de (2018). Abzocke online: Wie erkenne ich Fake-Shops im Internet? Internet https://www.verbraucherzentrale.de/wissen/digitale-welt/onlinehandel/abzocke-online-wie-erkenne-ich-fakeshops-im-internet-13166. Letzter Zugriff 25.11.2019.
• Wolf, P. (2019). Fakeshops erkennen: Online sicher einkaufen und gefälschte Onlineshops entlarven. Internet https://www.onlinewarnungen.de/ratgeber/fakeshops-erkennen-online-sicher-einkaufen. Letzter Zugriff 25.11.2019.
27 November 2019.