Financial Forensics · End Term · Jan 2023 · AN

Which of the following would not appear in the financing section of the statement of cash flows?

Which of the following ratios is used to analyse liquidity?

On January 1, 2017. XYZ Company started the year with a ₹ 300,000 in Retained Earnings, a ₹ 50,000 balance in Common Stock, and a ₹ 300,000 balance in Additional Paid-in Capital. During 2017, the company earned net income of ₹ 45,000, declared a dividend of ₹ 15,000, and issued 900 additional shares of stock (par value of ₹ 1 per share) for ₹ 10,000. What is total stockholders' equity on December 31, 2017?

An increasing inventory turnover ratio

If a company reported the following items on its income statement (cost of goods sold ₹ 8,000, income tax expense ₹ 2,000, interest expense ₹ 500, operating expenses ₹ 4,500, sales revenue ₹ 15,000), what amount would be reported for the subtotal "income from operations"?

Which of the following regarding retained earnings is false?

Christina will receive annuity payments of ₹ 1,200 a year for five years, with the first payment occurring at Year 4. What is the value of this annuity to her today at a discount rate of 7.25 percent?

You are considering two independent projects that have differing requirements. Project A has a required return of 12 percent compared to Project B’s required return of 13.5 percent. Project A costs ₹ 75,000 and has cash flows of ₹ 21,000, ₹ 49,000, and ₹ 12,000 for Years 1 to 3, respectively. Project B has an initial cost of ₹ 70,000 and cash flows of ₹ 15,000, ₹ 18,000, and ₹ 41,000 for Years 1 to 3, respectively. Based on the NPV, you should:

Penn Corp. wants to have a weighted average cost of capital of 8.7 percent. The firm has an after- tax cost of debt of 5.3 percent and a cost of equity of 10.65 percent. What debt-equity ratio is needed for the firm to achieve its targeted weighted average cost of capital?

Holmes, Inc., is an all-equity financed firm. The beta is 0.60, the market risk premium is 6.67 percent, and the risk-free rate is 3.30 percent. What is the expected rate of return on this stock?

Industries became Industri. This is an example of which of the following?

Input – Data scientists use a variety of tools and techniques to analyze large amounts of data and extract valuable insights Output – Data scientists use variety tools techniques analyze large amounts data extract valuable insights Which of the following pre-processing to input results in this output?

As given in the confusion matrix of the classifier in Table 1, a bank provides loan to 300 prospects from a database. Selection of an actual good customer leads to an average profit of ₹12,000. Due to misclassification, if a bad applicant is selected for loan, an average loss of ₹40,000 will be incurred. Based on the data given in the confusion matrix (Table 1), what is the additional profit bank could have earned by giving loans to declined good customers?

What is the number of False Negatives? PS: 1 is positive class, 0 is negative class

What is the rollback rate for D?

What is the roll forward rate for C?

What is the capture rate of B at top 20% (top 2 deciles)?

Y is a metric that is used to decide if a model has to be trained again. It captures the change in environment in which model was trained relative to the environment in which the model is deployed. What is Y?

Chennai Super Kings (CSK) team in IPL has trained a model using past IPL data to predict toss decision by taking ground factors, weather, team and time details. The PSI of the model in IPL 2023 is 0.23. Which of the following should be CSK’s next steps?

Joey had taken a credit of 200$ from the Chandler Bank. He had missed 2 instalments in total in the last 6 months and he has missed to pay the 5\(^{th}\) and 6\(^{th}\) month instalment. Which of the following delinquency buckets he fall into?

A fintech company has a ML system that identifies transaction frauds that occur in its system. The model currently has a recall of 99.9%. The fraud rate, as reported by the company in its system is 20 BPS. On a regular day there are close to above 1 million transactions that happens via the company’s payment system and for each fraudulent transaction the company losses INR 10 on an average. The annual savings (INR) brought in by the ML system is:

Which of the following performance metric is more suitable for the business problem below: A fintech company wants to build a fraud detection model that prevents fraudulent transactions happening in its ecosystem. The company is very particular about customer satisfaction and so they are very particular about not stopping a genuine customer in completing their transaction, but they are reasonably fine to flag a fraudulent transaction as a good transaction.

The following are the number of payments attempts on a regular day that a fintech giant is seeing in its platform. You are hired as a data scientist to find the pattern in the login attempts and you decide to perform a MLE with a gaussian distribution as an assumption. Which of these correctly represents the parameters of the normal distribution based on MLE for the given data: # payment attempts = 7,5,9,1,5,6,7,11,15,2,10

For the given confusion matrix below which of the following is True assuming Fraud as positive class and non-Fraud as negative class?

Precision score for the above confusion matrix is:

In isolation forest the points that are hard to separate from other points form the anomalies:

Which of the following cannot be solved by the differencing technique in time series analysis?

An autoregressive model of order 3 is denoted by which of the following equations?

There are two time series models A and B which have the following predictions, which of these is more accurate from the perspective for MSE? True value = [10, 12, 11, 15, 18, 20, 23] Predictions of A = [6, 15,11, 14, 15, 25, 21] Predictions of B = [7, 10, 12, 18, 16, 18, 24]

which of the following metrics can be used for computing the performance of an Auto-Regressive time series model.

Which of the following statements are False with respect to ACF and PACF plots I. ACF plots are used to determining the order of Autoregressive models. II. PACF plots are used to determining the order of Autoregressive models. III. ACF plots just computes the Pearson’s correlation between the variable and it’s lagged versions. IV. PACF plots just computes the Pearson’s correlation between the variable and it’s lagged versions.

You have the following 2 documents with the text: D1 = Lets change the logo of the company. D2 = The investors don’t like if the logo of the company is changed as logo plays a key role in brand recognition The Term Frequency (TF) for the work “company” for D1 and D2 is :

The following metrics can be used to calculate string similarity:

If cosine similarity between two string vectors is low, it means

You had converted two words to a vectors having following values: A = [2,1,4,2,8] B = [3,4,2,5,4] The cosine similarity between them is:

You had converted two words to a vectors having following values: A = [2,1,4,2,8] B = [3,4,3,5,5] The cosine similarity between them is:

In the following waterfall plot , identify the model predicted value.

Cohort explainability is the process of understanding to what degree your model’s features contribute to its predictions over a whole training data

From the following feature powerset , evaluate the ‘w4’ , weight of the marginal coalition.

Which of the following chart types is/are available in shap.summary_plot used for global interpretation of a model.

What is the purpose of ‘interaction_index’ in SHAP dependence plots