Suppose you are working for a financial institution and you are asked to implement a fraud...
Fantastic news! We've Found the answer you've been seeking!
Question:
Transcribed Image Text:
Suppose you are working for a financial institution and you are asked to implement a fraud detection system. You plan to use the following information: • When the card holder is travelling abroad, fraudulent transactions are more likely since tourists are prime targets for thieves. More precisely, 1% of transactions are fraudulent when the card holder is travelling, where as only 0.4% of the transactions are fraudulent when she is not travelling. On average, 5% of all transactions happen while the card holder is travelling. If a transaction is fraudulent, then the likelihood of a foreign purchase increases, unless the card holder happens to be travelling. More precisely, when the card holder is not travelling, 10% of the fraudulent transactions are foreign purchases where as only 1% of the legitimate transactions are foreign purchases. On the other hand, when the card holder is travelling, then 90% of the transactions are foreign purchases regardless of the legitimacy of the transactions. • Purchases made over the internet are more likely to be fraudulent. This is especially true for card holders who don't own any computer. Currently, 75% of the population owns a computer or smart phone and for those card holders, 1% of their legitimate transactions are done over the internet, however this percentage increases to 2% for fraudulent transactions. For those who don't own any computer or smart phone, a mere 0.1% of their legitimate transactions is done over the internet, but that number increases to 1.1% for fraudulent transactions. Unfortunately, the credit card company doesn't know whether a card holder owns a computer or smart phone, however it can usually guess by verifying whether any of the recent transactions involve the purchase of computer related accessories. In any given week, 10% of those who own a computer or smart phone purchase (with their credit card) at least one computer related item as opposed to just 0.1% of those who don't own any computer or smart phone. a) Construct a Bayes Network to identify fraudulent transactions. What to hand in: Show the graph defining the network and the Conditional Probability Tables associated with each node in the graph. This network should encode the information stated above. Your network should contain exactly six nodes, corresponding to the following binary random variables: OC: card holder owns a computer or smart phone. Fraud : current transaction is fraudulent. Trav : card holder is currently travelling. FP : current transaction is a foreign purchase. IP : current purchase is an internet purchase. CRP : a computer related purchase was made in the past week. The arcs defining your Network should accurately capture the probabilistic dependencies between these variables. b) What is the prior probability (i.e., before we search for previous computer related purchases and before we verify whether it is a foreign and/or an internet purchase) that the current transaction is a fraud? What is the probability that the current transaction is a fraud once we have verified that it is a foreign transaction, but not an internet purchase and that the card holder purchased computer related accessories in the past week? What to hand in: Indicate the two queries (i.e., Pr(variables evidence)) you used to compute those two probabil- ities. Show each step of the calculation Suppose you are working for a financial institution and you are asked to implement a fraud detection system. You plan to use the following information: • When the card holder is travelling abroad, fraudulent transactions are more likely since tourists are prime targets for thieves. More precisely, 1% of transactions are fraudulent when the card holder is travelling, where as only 0.4% of the transactions are fraudulent when she is not travelling. On average, 5% of all transactions happen while the card holder is travelling. If a transaction is fraudulent, then the likelihood of a foreign purchase increases, unless the card holder happens to be travelling. More precisely, when the card holder is not travelling, 10% of the fraudulent transactions are foreign purchases where as only 1% of the legitimate transactions are foreign purchases. On the other hand, when the card holder is travelling, then 90% of the transactions are foreign purchases regardless of the legitimacy of the transactions. • Purchases made over the internet are more likely to be fraudulent. This is especially true for card holders who don't own any computer. Currently, 75% of the population owns a computer or smart phone and for those card holders, 1% of their legitimate transactions are done over the internet, however this percentage increases to 2% for fraudulent transactions. For those who don't own any computer or smart phone, a mere 0.1% of their legitimate transactions is done over the internet, but that number increases to 1.1% for fraudulent transactions. Unfortunately, the credit card company doesn't know whether a card holder owns a computer or smart phone, however it can usually guess by verifying whether any of the recent transactions involve the purchase of computer related accessories. In any given week, 10% of those who own a computer or smart phone purchase (with their credit card) at least one computer related item as opposed to just 0.1% of those who don't own any computer or smart phone. a) Construct a Bayes Network to identify fraudulent transactions. What to hand in: Show the graph defining the network and the Conditional Probability Tables associated with each node in the graph. This network should encode the information stated above. Your network should contain exactly six nodes, corresponding to the following binary random variables: OC: card holder owns a computer or smart phone. Fraud : current transaction is fraudulent. Trav : card holder is currently travelling. FP : current transaction is a foreign purchase. IP : current purchase is an internet purchase. CRP : a computer related purchase was made in the past week. The arcs defining your Network should accurately capture the probabilistic dependencies between these variables. b) What is the prior probability (i.e., before we search for previous computer related purchases and before we verify whether it is a foreign and/or an internet purchase) that the current transaction is a fraud? What is the probability that the current transaction is a fraud once we have verified that it is a foreign transaction, but not an internet purchase and that the card holder purchased computer related accessories in the past week? What to hand in: Indicate the two queries (i.e., Pr(variables evidence)) you used to compute those two probabil- ities. Show each step of the calculation
Expert Answer:
Answer rating: 100% (QA)
Step 1 Establish project objectives measurement measures and resource allocationDefining the project goals is the first stage in every data science projectWhat kind of fraud cases did we wish to findW... View the full answer
Related Book For
Posted Date:
Students also viewed these general management questions
-
Suppose you are working for a company that does business with Australia. Your company has closed a deal where you will provide consulting services to the Australian firm and they will pay you a sum...
-
You are working for a major U.S. corporation that wants to expand its reach globally and has narrowed the search to either Mexico or Japan. Your supervisor has asked you to prepare a memo that...
-
Suppose you are working for a fast-growing startup company, which we will call FastCo, and it is your job to write a software package that can maintain the set, E, of all the employees working for...
-
Dalmo Bhd is an investment holding company and currently it has 3 subsidiaries as stated below. Dalmo Bhd group of companies financial year end is 31st March. The shareholding structure of Dalmo...
-
A dyadic rational is a number of the form k/2n for some k, n Z. Prove that if a and b are real numbers and a < b, then there exists a dyadic rational q such that a < q < b.
-
In Exercises 37 through 44, sketch the region of integration for the given integral and set up an equivalent integral with the order of integration reversed. In 3 /3 Jo f(x, y) dy dx
-
With reference to Exercise 11.65, construct a \(99 \%\) confidence interval for \(\alpha\).
-
Smith made a contract to sell automatic rifles to a foreign country. Because the sale of such weapons to that country was illegal under an act of Congress, the U.S. government prosecuted Smith for...
-
Molin Corporation is a manufacturer that uses job-order costing. The company closes out any overapplied or underapplied overhead to Cost of Goods Sold at the end of the year. The company has supplied...
-
Consider the transportation table given below. Find an initial solution using the northwest corner rule. What special condition exists? Explain how you will proceed to solve the problem. TO...
-
Cardi borrowed $13,000 at 29% interest. If making $400 payments, how much will she pay back in total, including interest, for those purchases?
-
A light ray traveling through medium 1 with index of refraction \(n_{1}=1.70\) reaches the interface between medium 1 and medium 2 with index of refraction \(n_{2}=1.50\). (a) At what minimum angle...
-
A light ray travels up from the bottom of a tank containing oil (index of refraction \(n=1.48\) ). If the oil surface is smooth, at what minimum angle from the normal to that surface would the light...
-
What specialized provisions does the Act put in place for cases involving the removal and placement of Indian children?
-
A red laser light has a wavelength of \(700 \mathrm{~nm}\) in air. What are the frequency and wavelength of this light in flint glass (index of refraction \(n=1.65\) )?
-
What is the index of refraction of a material in which the speed of light is \(20 \%\) less than the speed of light in vacuum?
-
21)When pareduc is added as a separate variable to the equation the model becomes a below: log(wage) = 4.94 (0.38) (0.027) (0.017) 0.097 educ+ 0.033 pareduc- 0.0026 educ>pareduc (0.0012) +0.020...
-
What are the four types of poultry production systems? Explain each type.
-
What is the relationship between corruption in a country (i.e., bribe taking by government officials) and economic growth? Is corruption always bad?
-
What are the economic and political arguments for regional economic integration? Given these arguments, why dont we see more substantial examples of integration in the world economy?
-
Reread the Management Focus box on the alliance between Cisco and Fujitsu. What are the benefits to Cisco and Fujitsu respectively of the alliances? What are the risks to Cisco? How can Cisco...
-
If the sample standard deviations instead of the sample ranges are used to estimate \(\sigma\), the control limits for the resulting \(\bar{x}\) chart are given by \(\overline{\bar{x}} \pm A_{1}...
-
In order to establish control charts for an extraction job, 30 samples of five measurements of the extracted ores are taken, and the results are \(\overline{\bar{x}}=25.96\) tons and \(\bar{s}=1.5\)...
-
Suppose that with the samples of Exercise 15.6, it is desired to establish control also over the variability of the process. Using the method of Exercise 15.5 and the values of \(\overline{\bar{x}}\)...
Study smarter with the SolutionInn App