OneAssist Consumer Solutions Data Scientist Interview Questions and Answers

Focus on little bit of dynamic programming

Q1. Apache spark architecture and ecosystem along with memory management
Add your answer
Q2. SQL queries for manager salary
Add your answer
Q3. Python decorators --> @
Add your answer
Q4. RANK and other window functions
Add your answer
Q5. Joins along with use case
Ans. 
Joins are used in SQL to combine rows from two or more tables based on a related column between them.
• Joins are used to retrieve data from multiple tables based on a related column

• Common types of joins include INNER JOIN, LEFT JOIN, RIGHT JOIN, and FULL JOIN

• Use cases for joins include combining customer data with order data, merging employee information with department details
Answered by AI
Add your answer

30 min - basic Python coding

Q1. DataEngineering Basic Questins
Add your answer
Q2. Personality based questions
Add your answer

Q1. What is correlation(in plain english)?
Ans. 
Correlation is a statistical measure that shows how two variables are related to each other.
• Correlation measures the strength and direction of the relationship between two variables.

• It ranges from -1 to 1, where -1 indicates a perfect negative correlation, 0 indicates no correlation, and 1 indicates a perfect positive correlation.

• Correlation does not imply causation, meaning that just because two variables are correlat...read more
Answered by AI
Add your answer
Q2. What is multi-collinearity?
Ans. 
Multicollinearity is a phenomenon where two or more independent variables in a regression model are highly correlated.
• It can lead to unstable and unreliable estimates of regression coefficients.

• It can also make it difficult to determine the individual effect of each independent variable on the dependent variable.

• It can be detected using correlation matrices or variance inflation factors (VIF).

• Solutions include removing...read more
Answered by AI
Add your answer
Q3. What are p-values? explain it in plain english without bringing up machine learning?
Ans. 
P-values are a statistical measure that helps determine the likelihood of obtaining a result by chance.
• P-values range from 0 to 1, with a smaller value indicating stronger evidence against the null hypothesis.

• A p-value of 0.05 or less is typically considered statistically significant.

• P-values are commonly used in hypothesis testing to determine if a result is statistically significant or not.
Answered by AI
Add your answer
Q4. How are LSTMs better than RNNs? what makes them better? how does LSTMs do better what they do better than vanilla RNNs?
Ans. 
LSTMs are better than RNNs due to their ability to handle long-term dependencies.
• LSTMs have a memory cell that can store information for long periods of time.

• They have gates that control the flow of information into and out of the cell.

• This allows them to selectively remember or forget information.

• Vanilla RNNs suffer from the vanishing gradient problem, which limits their ability to handle long-term dependencies.

• LSTMs ...read more
Answered by AI
Add your answer
Q5. Does pooling in CNNs have any learning?
Ans. 
Pooling in CNNs has learning but reduces spatial resolution.
• Pooling helps in reducing overfitting by summarizing the features learned in a region.

• Max pooling retains the strongest feature in a region while average pooling takes the average.

• Pooling reduces the spatial resolution of the feature maps.

• Pooling can also help in translation invariance.

• However, too much pooling can lead to loss of important information.
Answered by AI
Add your answer
Q6. Why does optimisers matter? what's their purpose? what do they do in addition to weights-updation that the vanilla gradient and back-prop does?
Ans. 
Optimizers are used to improve the efficiency and accuracy of the training process in machine learning models.
• Optimizers help in finding the optimal set of weights for a given model by minimizing the loss function.

• They use various techniques like momentum, learning rate decay, and adaptive learning rates to speed up the training process.

• Optimizers also prevent the model from getting stuck in local minima and help in ge...read more
Answered by AI
Add your answer
Q7. What does KNN do during training?
Ans. 
KNN during training stores all the data points and their corresponding labels to use for prediction.
• KNN algorithm stores all the training data points and their corresponding labels.

• It calculates the distance between the new data point and all the stored data points.

• It selects the k-nearest neighbors based on the calculated distance.

• It assigns the label of the majority of the k-nearest neighbors to the new data point.
Answered by AI
Add your answer
Q8. You have two different vectors with only small change in one of the dimensions. but, the predictions/output from the model is drastically different for each vector. can you explain why this can be the case...read more
Ans. 
Small change in one dimension causing drastic difference in model output. Explanation and solution.
• This is known as sensitivity to input

• It can be caused by non-linearities in the model or overfitting

• Regularization techniques can be used to reduce sensitivity

• Cross-validation can help identify overfitting

• Ensemble methods can help reduce sensitivity

• It is generally a bad thing as it indicates instability in the model
Answered by AI
Add your answer
Q9. Slope vs gradient (again not in relation to machine learning, and in plain english)
Ans. 
Slope and gradient are both measures of the steepness of a line, but slope is a ratio while gradient is a vector.
• Slope is the ratio of the change in y to the change in x on a line.

• Gradient is the rate of change of a function with respect to its variables.

• Slope is a scalar value, while gradient is a vector.

• Slope is used to describe the steepness of a line, while gradient is used to describe the direction and magnitude o...read more
Answered by AI
Add your answer
Q10. How are boosting and bagging algorithms different?
Ans. 
Boosting and bagging are ensemble learning techniques used to improve model performance.
• Bagging involves training multiple models on different subsets of the data and averaging their predictions.

• Boosting involves training multiple models sequentially, with each model focusing on the errors of the previous model.

• Bagging reduces variance and overfitting, while boosting reduces bias and underfitting.

• Examples of bagging al...read more
Answered by AI
Add your answer
Q11. What is a logarithm? (in linear algebra) what is it's significance and what purpose does it serve?
Ans. 
A logarithm is a mathematical function that measures the relationship between two quantities.
• Logarithms are used to simplify complex calculations involving large numbers.

• They are used in linear algebra to transform multiplicative relationships into additive ones.

• Logarithms are also used in data analysis to transform skewed data into a more normal distribution.

• Common logarithms use base 10, while natural logarithms use
Answered by AI
Add your answer
Q12. What are gradients? (not in relation to machine learning)
Ans. 
Gradients are the changes in values of a function with respect to its variables.
• Gradients are used in calculus to measure the rate of change of a function.

• They are represented as vectors and indicate the direction of steepest ascent.

• Gradients are used in optimization problems to find the minimum or maximum value of a function.

• They are also used in physics to calculate the force acting on a particle.

• Gradients can be cal
Answered by AI
Add your answer

Q1. Time Series forecasting questions
Add your answer

Q1. What is shebang in bash scripting
Ans. 
Shebang is a special character sequence used in Unix-based systems to indicate the interpreter for a script file.
• Shebang starts with #! and is followed by the path to the interpreter

• It is used to specify the interpreter for a script file

• It allows the script to be executed without explicitly invoking the interpreter

• Example: #!/bin/bash specifies that the script should be run using the bash interpreter
Answered by AI
Add your answer
Q2. Explain vector projection
Ans. 
Vector projection is the process of projecting a vector onto another vector.
• It involves finding the component of one vector that lies along another vector.

• The result is a scalar value that represents the length of the projection.

• The projection can be calculated using the dot product of the two vectors.

• The formula for vector projection is proj_u(v) = (u . v / ||u||^2) * u.

• Vector projection is used in various fields such
Answered by AI
Add your answer
Q3. Who is a leader and qualities of leader.
Ans. 
A leader is someone who guides and inspires others towards a common goal.
• A leader possesses strong communication skills and can effectively convey their vision and goals to their team.

• A leader is able to motivate and inspire their team members, encouraging them to perform at their best.

• A leader is knowledgeable and experienced in their field, earning the respect and trust of their team.

• A leader is able to make tough de...read more
Answered by AI
Add your answer
Q4. A week to spend on answering a question on Probability of collision of two objects.
Add your answer
Q5. How do you convert 3d object collision problem to 2d collision problem
Ans. 
3D object collision problem can be converted to 2D by projecting the objects onto a 2D plane.
• Project the 3D objects onto a 2D plane using a projection matrix.

• Calculate the 2D coordinates of the projected objects.

• Perform collision detection in 2D using standard algorithms.

• Example: projecting a sphere onto a 2D plane results in a circle.

• Example: projecting a cube onto a 2D plane results in a square.
Answered by AI
Add your answer

Q1. Why are you interested in smartsheet
Add your answer
Q2. Tell me about your ds background
Add your answer

Q1. Case interview question.
Add your answer

Q1. What is your Experience in Deploying ML Models
Ans. 
I have experience deploying ML models in production environments using cloud services like AWS and Azure.
• Deployed ML models using AWS SageMaker for real-time predictions

• Utilized Azure Machine Learning service to deploy models for batch processing

• Implemented CI/CD pipelines for automated model deployment

• Managed model versioning and monitoring in production environments
Answered by AI
Add your answer
Q2. What is your Expertise in deep learning methodologies
Ans. 
I have expertise in deep learning methodologies including neural networks, CNNs, RNNs, and GANs.
• Extensive experience with neural networks and their applications in image recognition and natural language processing

• Proficient in Convolutional Neural Networks (CNNs) for tasks such as image classification and object detection

• Familiarity with Recurrent Neural Networks (RNNs) for sequential data analysis like time series for...read more
Answered by AI
Add your answer

Q1. Model evaluation methods to check model performance
Ans. 
Various model evaluation methods are used to check the performance of a data science model.
• Cross-validation: splitting data into multiple subsets for training and testing

• Confusion matrix: evaluating classification models based on true positives, true negatives, false positives, and false negatives

• ROC curve: plotting the true positive rate against the false positive rate

• Precision, recall, and F1 score: metrics for evalu...read more
Answered by AI
Add your answer
Q2. Projects done so far with tech explanation
Ans. 
I have worked on projects involving machine learning algorithms for predictive analytics and natural language processing.
• Developed a predictive model using random forest algorithm to forecast customer churn in a telecom company.

• Implemented sentiment analysis using natural language processing techniques to analyze customer reviews for a retail company.

• Utilized deep learning techniques such as LSTM for time series foreca
Answered by AI
Add your answer