Upload Button Icon Add office photos

Filter interviews by

American Express Data Scientist Interview Questions and Answers

Updated 27 Sep 2024

American Express Data Scientist Interview Experiences

3 interviews found

Data Scientist Interview Questions & Answers

user image Rohan Soni

posted on 20 Jul 2024

Interview experience
5
Excellent
Difficulty level
-
Process Duration
-
Result
-
Round 1 - Technical 

(2 Questions)

  • Q1. How do you define model Gini?
  • Ans. 

    Model Gini is a measure of statistical dispersion used to evaluate the performance of classification models.

    • Model Gini is calculated as twice the area between the ROC curve and the diagonal line (random model).

    • It ranges from 0 (worst model) to 1 (best model), with higher values indicating better model performance.

    • A Gini coefficient of 0.5 indicates a model that is no better than random guessing.

    • Commonly used in credit

  • Answered by AI
  • Q2. How to you train XG boost model
  • Ans. 

    XGBoost model is trained by specifying parameters, splitting data into training and validation sets, fitting the model, and tuning hyperparameters.

    • Specify parameters for XGBoost model such as learning rate, max depth, and number of trees

    • Split data into training and validation sets using train_test_split function

    • Fit the XGBoost model on training data using fit method

    • Tune hyperparameters using techniques like grid search

  • Answered by AI

Skills evaluated in this interview

Interview experience
5
Excellent
Difficulty level
-
Process Duration
-
Result
-
Round 1 - Aptitude Test 

Many Mcq,s.Similar to cat exam

Round 2 - Case Study 

Ml case study . Eg loan default prediction

Data Scientist Interview Questions Asked at Other Companies

Q1. for a data with 1000 samples and 700 dimensions, how would you fi ... read more
Q2. Special Sum of Array Problem Statement Given an array 'arr' conta ... read more
asked in Affine
Q3. you have a pandas dataframe with three columns, filled with state ... read more
Q4. Clone a Linked List with Random Pointers Given a linked list wher ... read more
asked in Coforge
Q5. coding question of finding index of 2 nos. having total equal to ... read more
Interview experience
4
Good
Difficulty level
Hard
Process Duration
Less than 2 weeks
Result
Selected Selected

I applied via Campus Placement and was interviewed before Jul 2023. There were 3 interview rounds.

Round 1 - Aptitude Test 

Medium General Aptitude questions and technical(Big Data, Python etc.)

Round 2 - Technical 

(1 Question)

  • Q1. ML Algorithms (SVM, Random forest, bagging boosting, ridge, etc)
Round 3 - Technical 

(1 Question)

  • Q1. Deep equations and understading of DL and ML Algorithms
  • Ans. 

    Understanding deep equations and algorithms in DL and ML is crucial for a data scientist.

    • Deep learning involves complex neural network architectures like CNNs and RNNs.

    • Machine learning algorithms include decision trees, SVM, k-means clustering, etc.

    • Understanding the math behind algorithms helps in optimizing model performance.

    • Equations like gradient descent, backpropagation, and loss functions are key concepts.

    • Practica...

  • Answered by AI

Skills evaluated in this interview

Interview questions from similar companies

I applied via Recruitment Consulltant and was interviewed before Aug 2021. There was 1 interview round.

Round 1 - Technical 

(1 Question)

  • Q1. Difference between CNN and MLP
  • Ans. 

    CNN is used for image recognition while MLP is used for general classification tasks.

    • CNN uses convolutional layers to extract features from images while MLP uses fully connected layers.

    • CNN is better suited for tasks that require spatial understanding like object detection while MLP is better for tabular data.

    • CNN has fewer parameters than MLP due to weight sharing in convolutional layers.

    • CNN can handle input of varying

  • Answered by AI

Interview Preparation Tips

Interview preparation tips for other job seekers - Brush up basic statistics . Also prepare atleast 2 , 3 ML algorithms for the interview.

Skills evaluated in this interview

Interview experience
1
Bad
Difficulty level
-
Process Duration
-
Result
-
Round 1 - One-on-one 

(1 Question)

  • Q1. How to extract numbers pre decimal point from a long list of decimalnumbers with efficiency
  • Ans. 

    Use string manipulation to efficiently extract numbers before the decimal point from a list of decimal numbers.

    • Split each decimal number by the decimal point and extract the number before it

    • Use regular expressions to match and extract numbers before the decimal point

    • Iterate through the list and extract numbers using string manipulation functions

  • Answered by AI

Skills evaluated in this interview

Interview experience
5
Excellent
Difficulty level
-
Process Duration
-
Result
-
Round 1 - Coding Test 

I was asked Python, sql, coding questions

Round 2 - Case Study 

Case study on how would you identify the total number of footfall on a airport

Interview experience
5
Excellent
Difficulty level
-
Process Duration
-
Result
-

I applied via Campus Placement

Round 1 - Technical 

(1 Question)

  • Q1. Work done in previous companty
  • Ans. 

    Developed machine learning models to predict customer churn and optimize marketing campaigns.

    • Built predictive models using Python and scikit-learn

    • Utilized SQL to extract and manipulate data for analysis

    • Collaborated with cross-functional teams to implement data-driven solutions

  • Answered by AI

Interview Questionnaire 

3 Questions

  • Q1. Mainly resume based. In detail from the project.
  • Q2. Softmax vs sigmoid
  • Ans. 

    Softmax and sigmoid are both activation functions used in neural networks.

    • Softmax is used for multi-class classification problems, while sigmoid is used for binary classification problems.

    • Softmax outputs a probability distribution over the classes, while sigmoid outputs a probability for a single class.

    • Softmax ensures that the sum of the probabilities of all classes is 1, while sigmoid does not.

    • Softmax is more sensitiv...

  • Answered by AI
  • Q3. Logistics regression (multiclass)

Interview Preparation Tips

Interview preparation tips for other job seekers - Prepare the projects mentioned in your resume very well

Skills evaluated in this interview

Interview experience
3
Average
Difficulty level
Moderate
Process Duration
2-4 weeks
Result
-

I applied via Company Website and was interviewed before Feb 2023. There was 1 interview round.

Round 1 - Technical 

(1 Question)

  • Q1. ML concepts , regression, regularization etc
Interview experience
3
Average
Difficulty level
Moderate
Process Duration
Less than 2 weeks
Result
Not Selected

I applied via Referral and was interviewed before May 2023. There was 1 interview round.

Round 1 - Technical 

(2 Questions)

  • Q1. Self Intro and projects discussion
  • Q2. Feature selection methods
  • Ans. 

    Feature selection methods help in selecting the most relevant features for building predictive models.

    • Feature selection methods aim to reduce the number of input variables to only those that are most relevant.

    • Common methods include filter methods, wrapper methods, and embedded methods.

    • Examples include Recursive Feature Elimination (RFE), Principal Component Analysis (PCA), and Lasso regression.

  • Answered by AI

Skills evaluated in this interview

American Express Interview FAQs

How many rounds are there in American Express Data Scientist interview?
American Express interview process usually has 2 rounds. The most common rounds in the American Express interview process are Technical, Aptitude Test and Case Study.
How to prepare for American Express Data Scientist interview?
Go through your CV in detail and study all the technologies mentioned in your CV. Prepare at least two technologies or languages in depth if you are appearing for a technical interview at American Express. The most common topics and skills that interviewers at American Express expect are Career Development, Stakeholder Management, Agile Coaching, Data Analytics and Econometrics.
What are the top questions asked in American Express Data Scientist interview?

Some of the top questions asked at the American Express Data Scientist interview -

  1. Deep equations and understading of DL and ML Algorit...read more
  2. How to you train XG boost mo...read more
  3. How do you define model Gi...read more

Tell us how to improve this page.

American Express Data Scientist Interview Process

based on 4 interviews

Interview experience

4.8
  
Excellent
View more
American Express Data Scientist Salary
based on 127 salaries
₹10 L/yr - ₹32 L/yr
53% more than the average Data Scientist Salary in India
View more details

American Express Data Scientist Reviews and Ratings

based on 9 reviews

4.3/5

Rating in categories

3.3

Skill development

4.5

Work-life balance

3.9

Salary

4.8

Job security

4.8

Company culture

3.8

Promotions

3.9

Work satisfaction

Explore 9 Reviews and Ratings
Business Analyst
872 salaries
unlock blur

₹9.6 L/yr - ₹17 L/yr

Assistant Manager
716 salaries
unlock blur

₹14 L/yr - ₹42 L/yr

Senior Analyst
608 salaries
unlock blur

₹14.8 L/yr - ₹26.9 L/yr

Analyst
571 salaries
unlock blur

₹12.6 L/yr - ₹27 L/yr

Lead Analyst
534 salaries
unlock blur

₹4.3 L/yr - ₹13.5 L/yr

Explore more salaries
Compare American Express with

MasterCard

3.9
Compare

Wells Fargo

3.8
Compare

JPMorgan Chase & Co.

3.9
Compare

HSBC Group

3.9
Compare
Did you find this page helpful?
Yes No
write
Share an Interview