Data Science Intern

filter-iconFilter interviews by

100+ Data Science Intern Interview Questions and Answers

Updated 17 Jan 2025

Q51. difference between array and linkedlist,stack and queue

Ans.

Arrays store elements in contiguous memory, while linked lists use nodes with pointers. Stacks follow LIFO, queues follow FIFO.

  • Arrays store elements in contiguous memory locations, allowing for constant time access to elements using indices.

  • Linked lists use nodes with pointers to the next node, allowing for dynamic memory allocation and insertion/deletion at any position.

  • Stacks follow Last In First Out (LIFO) principle, where elements are added and removed from the same end (...read more

Q52. Why do you want to pursue data science

Ans.

I want to pursue data science because of my passion for analyzing and interpreting data to solve complex problems.

  • I enjoy working with data and finding patterns and insights

  • I want to use my skills to help businesses make data-driven decisions

  • Data science is a rapidly growing field with endless opportunities

  • I have experience in programming and statistics, which are essential skills for data science

  • For example, I have worked on projects analyzing customer behavior and predictin...read more

Q53. Which is the best clustering algorithm?

Ans.

There is no one-size-fits-all answer as the best clustering algorithm depends on the specific dataset and goals.

  • The best clustering algorithm depends on the dataset characteristics such as size, dimensionality, and noise level.

  • K-means is popular for its simplicity and efficiency, but may not perform well on non-linear data.

  • DBSCAN is good for clusters of varying shapes and sizes, but may struggle with high-dimensional data.

  • Hierarchical clustering is useful for visualizing clus...read more

Q54. How to handle missing data in a dataset?

Ans.

Missing data can be handled by imputation, deletion, or using algorithms that can handle missing values.

  • Imputation: Fill missing values with mean, median, mode, or using predictive modeling.

  • Deletion: Remove rows or columns with missing values.

  • Algorithms: Use algorithms like Random Forest, XGBoost, or LightGBM that can handle missing values.

  • Consider the reason for missing data and choose the appropriate method for handling it.

Are these interview questions helpful?

Q55. How did you use that particular ML algorithm

Ans.

I used the Random Forest algorithm to predict customer churn in a telecom company.

  • Preprocessed the data by handling missing values and encoding categorical variables

  • Split the data into training and testing sets

  • Tuned hyperparameters using grid search

  • Trained the Random Forest model on the training data

  • Evaluated the model's performance using metrics like accuracy, precision, recall, and F1 score

  • Interpreted feature importance to understand key drivers of customer churn

Q56. What are Regularization Techniques ?

Ans.

Regularization techniques are methods used to prevent overfitting in machine learning models by adding a penalty term to the loss function.

  • Regularization techniques help in reducing the complexity of the model by penalizing large coefficients.

  • Common regularization techniques include L1 regularization (Lasso), L2 regularization (Ridge), and Elastic Net regularization.

  • Regularization helps in improving the generalization of the model by preventing it from fitting noise in the tr...read more

Share interview questions and help millions of jobseekers 🌟

man-with-laptop

Q57. what is a logistic regression model?

Ans.

Logistic regression is a statistical model used to predict the probability of a binary outcome based on one or more predictor variables.

  • Logistic regression is used when the dependent variable is binary (0/1, True/False, Yes/No, etc.)

  • It estimates the probability that a given input belongs to a particular category.

  • The model calculates the odds of the event happening.

  • It uses a logistic function to map the input values to the output probability.

  • Example: Predicting whether an emai...read more

Q58. difference between supervised and unsupervised learning

Ans.

Supervised learning uses labeled data to train the model, while unsupervised learning uses unlabeled data.

  • Supervised learning requires a target variable to predict, while unsupervised learning does not.

  • In supervised learning, the model learns from the labeled training data and makes predictions on new data. In unsupervised learning, the model finds patterns and relationships in the data without guidance.

  • Examples of supervised learning include classification and regression tas...read more

Data Science Intern Jobs

Data Science Intern 0-1 years
IT Education Centre
4.5
Pune
Data Science Intern 0-1 years
Feynn Labs
4.0
Guwahati
Data Science Internship 1-5 years
Prodigy InfoTech
3.8
Mumbai

Q59. Which programming language do you use?

Ans.

I primarily use Python for data science projects.

  • Python is widely used in the data science community for its simplicity and versatility.

  • It has a large number of libraries and frameworks specifically designed for data analysis and machine learning, such as Pandas, NumPy, and Scikit-learn.

  • Python's syntax is easy to learn and understand, making it a popular choice for beginners and experienced programmers alike.

Q60. What are Large Language Models?

Ans.

Large Language Models are advanced AI models that can generate human-like text based on input data.

  • Large Language Models use deep learning techniques to understand and generate text.

  • Examples include GPT-3 (Generative Pre-trained Transformer 3) and BERT (Bidirectional Encoder Representations from Transformers).

  • They are trained on vast amounts of text data to improve their language generation capabilities.

Q61. How do you handle mutiple tasks

Ans.

I prioritize tasks based on deadlines and importance, use to-do lists and calendars, delegate when possible, and focus on one task at a time.

  • Prioritize tasks based on deadlines and importance

  • Use to-do lists and calendars to stay organized

  • Delegate tasks when possible to lighten the workload

  • Focus on one task at a time to avoid feeling overwhelmed

Q62. what do u know about python, ML, AI

Ans.

Python is a versatile programming language used for data analysis, ML involves creating algorithms that improve automatically through experience, AI is the simulation of human intelligence by machines.

  • Python is a popular programming language known for its simplicity and readability.

  • Machine Learning (ML) involves creating algorithms that can learn from and make predictions or decisions based on data.

  • Artificial Intelligence (AI) is the simulation of human intelligence processes...read more

Q63. What is Random Forest Classifier?

Ans.

Random Forest Classifier is an ensemble learning method that builds multiple decision trees and merges them to improve accuracy.

  • Random Forest is a collection of decision trees that work together to make predictions.

  • Each tree in the Random Forest is built using a subset of the training data and a random subset of features.

  • The final prediction is made by aggregating the predictions of all the individual trees, usually through voting or averaging.

  • Random Forest is a popular algor...read more

Q64. What is fax queries in Power BI

Ans.

Fax queries in Power BI are used to send queries to a data source via fax.

  • Fax queries allow users to send queries to a data source using fax technology.

  • This feature is useful for organizations that still rely on fax communication for data retrieval.

  • Fax queries can be set up in Power BI to automate the process of sending and receiving data via fax.

Q65. What is random forest? What it is called random?

Ans.

Random forest is an ensemble learning method used for classification and regression tasks, consisting of multiple decision trees.

  • Random forest is made up of multiple decision trees, where each tree is built using a subset of the training data and a random subset of features.

  • During prediction, each tree in the forest independently predicts the output, and the final output is determined by a majority vote (classification) or averaging (regression) of all the trees' predictions....read more

Q66. what are the regularization in ml

Ans.

Regularization in machine learning is a technique used to prevent overfitting by adding a penalty term to the model's loss function.

  • Regularization helps in reducing the complexity of the model by penalizing large coefficients.

  • Common types of regularization include L1 (Lasso) and L2 (Ridge) regularization.

  • L1 regularization adds the absolute value of the coefficients to the loss function, promoting sparsity.

  • L2 regularization adds the squared value of the coefficients to the los...read more

Q67. What is multinomial Naive Bayes theorem

Ans.

Multinomial Naive Bayes is a classification algorithm based on Bayes' theorem with the assumption of independence between features.

  • It is commonly used in text classification tasks, such as spam detection or sentiment analysis.

  • It is suitable for features that represent counts or frequencies, like word counts in text data.

  • It calculates the probability of each class given the input features and selects the class with the highest probability.

Q68. What is support vector machine?

Ans.

Support Vector Machine is a supervised machine learning algorithm used for classification and regression tasks.

  • Support Vector Machine finds the hyperplane that best separates different classes in the feature space

  • It works by maximizing the margin between the hyperplane and the nearest data points, known as support vectors

  • SVM can handle both linear and non-linear data by using different kernel functions like linear, polynomial, and radial basis function kernels

Q69. what is correlation ?

Ans.

Correlation is a statistical measure that describes the extent to which two variables change together.

  • Correlation ranges from -1 to 1, with 1 indicating a perfect positive correlation, -1 indicating a perfect negative correlation, and 0 indicating no correlation.

  • Correlation does not imply causation, meaning just because two variables are correlated does not mean that one causes the other.

  • Examples of correlation include the relationship between temperature and ice cream sales,...read more

Q70. Explain how a neural network works

Ans.

Neural networks are a type of machine learning algorithm inspired by the human brain, consisting of interconnected nodes that process information.

  • Neural networks consist of layers of interconnected nodes, each node performing a mathematical operation on the input data.

  • The output of each node is passed through an activation function to introduce non-linearity into the network.

  • Neural networks learn by adjusting the weights of connections between nodes during training, using alg...read more

Q71. Difference between Logistic and Linear Regression

Ans.

Logistic regression is used for binary classification while linear regression is used for regression tasks.

  • Logistic regression predicts the probability of a binary outcome (0 or 1) based on one or more independent variables.

  • Linear regression predicts a continuous outcome based on one or more independent variables.

  • Logistic regression uses a sigmoid function to map predicted values between 0 and 1, while linear regression uses a linear function.

  • Logistic regression is commonly u...read more

Q72. Difference between Random and ordering partition

Ans.

Random partition involves splitting data randomly, while ordering partition involves splitting data based on a specific order.

  • Random partition randomly divides data into subsets without any specific order.

  • Ordering partition divides data into subsets based on a specific order, such as time or alphabetical order.

  • Random partition is useful for creating training and testing sets for machine learning models.

  • Ordering partition is helpful for time series data analysis or when data n...read more

Q73. Python - All subsets of a list.

Ans.

Generate all possible subsets of a given list in Python.

  • Use itertools.combinations to generate all possible combinations of the list elements.

  • Convert the combinations to lists and store them in a new list to get all subsets.

Q74. What is naive in Naive Bayes?

Ans.

Naive Bayes assumes independence between features, hence 'naive'.

  • Naive Bayes assumes all features are independent of each other, which is often not true in real-world data.

  • Despite its simplifying assumption, Naive Bayes is still widely used in text classification and spam filtering.

  • The 'naive' assumption allows for fast and efficient classification, especially with large datasets.

Q75. Explain what are GANs?

Ans.

GANs are Generative Adversarial Networks, a type of deep learning model consisting of two neural networks - a generator and a discriminator.

  • GANs are used to generate new data samples that resemble a given dataset.

  • The generator network creates fake data samples, while the discriminator network tries to distinguish between real and fake samples.

  • The two networks are trained simultaneously in a competitive manner, improving each other's performance.

  • GANs have applications in image...read more

Q76. what is python basics, libraries

Ans.

Python basics include syntax, data types, and control structures. Libraries like NumPy, Pandas, and Matplotlib enhance data analysis and visualization.

  • Python basics cover syntax, variables, data types, and control structures.

  • NumPy is a library for numerical computing, providing powerful array operations.

  • Pandas is a library for data manipulation and analysis, offering data structures like DataFrames.

  • Matplotlib is a library for data visualization, allowing creation of various p...read more

Q77. what is Hypothesis testing

Ans.

Hypothesis testing is a statistical method used to make inferences about a population based on sample data.

  • It involves formulating a hypothesis about a population parameter, collecting data, and using statistical tests to determine if the data supports or rejects the hypothesis.

  • There are two types of hypotheses: null hypothesis (H0) and alternative hypothesis (H1).

  • Common statistical tests for hypothesis testing include t-tests, ANOVA, chi-square tests, and regression analysis...read more

Q78. What is Population and Sample

Ans.

Population refers to the entire group of individuals or items that we are interested in studying, while a sample is a subset of the population.

  • Population is the larger group that we want to draw conclusions about.

  • Sample is a smaller group selected from the population to represent it.

  • Population parameters are characteristics of the entire group, while sample statistics are characteristics of the sample.

  • Example: Population could be all students in a school, while a sample could...read more

Q79. what is Cost function.

Ans.

Cost function is a mathematical function that measures the error between predicted values and actual values in a machine learning model.

  • Cost function helps in optimizing the parameters of a model to minimize the error.

  • Common cost functions include Mean Squared Error (MSE) and Cross Entropy Loss.

  • It is used in training machine learning models through techniques like gradient descent.

  • The goal is to find the parameters that minimize the cost function.

Q80. What is ginni coefficient.

Ans.

Gini coefficient is a measure of statistical dispersion intended to represent the income or wealth distribution of a nation's residents.

  • Gini coefficient ranges from 0 to 1, where 0 represents perfect equality and 1 represents perfect inequality.

  • A Gini coefficient of 0.4 is considered moderate inequality, while 0.6 or higher is considered high inequality.

  • It is commonly used in economics to measure income inequality within a population.

  • The formula for calculating Gini coefficie...read more

Q81. Do you know about RAGs?

Ans.

RAGs stands for Red, Amber, Green. It is a project management tool used to visually indicate the status of tasks or projects.

  • RAGs is commonly used in project management to quickly communicate the status of tasks or projects.

  • Red typically indicates tasks or projects that are behind schedule or at risk.

  • Amber signifies tasks or projects that are on track but may require attention.

  • Green represents tasks or projects that are on schedule or completed successfully.

  • For example, a pro...read more

Q82. Explain OOP in Python

Ans.

OOP in Python is a programming paradigm where objects are created that contain data and methods to manipulate that data.

  • Classes are used to create objects in Python

  • Objects have attributes (data) and methods (functions)

  • Inheritance allows classes to inherit attributes and methods from other classes

  • Encapsulation allows data to be hidden and only accessed through methods

  • Polymorphism allows objects to be treated as instances of their parent class

Q83. what is convolution ?

Ans.

Convolution is a mathematical operation that combines two functions to produce a third function.

  • Convolution involves sliding one function over another and multiplying the overlapping values at each point.

  • It is commonly used in signal processing, image processing, and neural networks.

  • Example: Convolutional Neural Networks (CNNs) use convolution layers to extract features from input data.

Q84. Tell how a CNN model works

Ans.

CNN model uses convolutional layers to extract features from images and classify them.

  • Convolutional layers extract features from images by sliding a filter over the image and performing element-wise multiplication and summation

  • Pooling layers reduce the spatial dimensions of the feature maps while retaining important information

  • Fully connected layers use the extracted features to classify the image into different categories

  • Examples include image classification, object detectio...read more

Q85. What is classification and regression

Ans.

Classification is the process of categorizing data into predefined classes, while regression is the process of predicting continuous values.

  • Classification involves predicting the category or class label of new observations based on past data

  • Regression involves predicting a continuous value for new observations based on past data

  • Examples of classification include spam detection in emails and predicting whether a customer will churn

  • Examples of regression include predicting hous...read more

Q86. Market basket analysis algorithm

Ans.

Market basket analysis algorithm is used to identify the relationship between products frequently purchased together.

  • It is a data mining technique.

  • It helps in identifying the co-occurrence of items in a transactional database.

  • It is used in retail, e-commerce, and marketing industries.

  • It helps in cross-selling and up-selling products.

  • Example: If a customer buys bread, there is a high probability that they will also buy butter or jam.

  • Popular algorithms used for market basket an...read more

Q87. What is normalization?

Ans.

Normalization is the process of scaling and standardizing data to have a consistent range.

  • Normalization helps in comparing different features on the same scale.

  • Common normalization techniques include Min-Max scaling and Z-score normalization.

  • Example: Scaling age and income variables to a range of 0 to 1.

Frequently asked in, ,

Q88. What do you understand by LSTM

Ans.

LSTM stands for Long Short-Term Memory, a type of recurrent neural network architecture used for sequence prediction and time series forecasting.

  • LSTM networks are designed to overcome the vanishing gradient problem in traditional RNNs.

  • They have the ability to remember long-term dependencies in data sequences.

  • LSTMs have three gates: input gate, forget gate, and output gate, which control the flow of information.

  • They are widely used in natural language processing, speech recogn...read more

Q89. What is prompt engineering

Ans.

Prompt engineering involves designing and creating effective prompts to elicit specific responses from users or models.

  • Prompt engineering is the process of crafting prompts to guide users or models towards desired outcomes.

  • It involves understanding the target audience and tailoring prompts to be clear, concise, and engaging.

  • Examples include designing survey questions to gather specific information or creating prompts for chatbots to prompt user interactions.

Q90. Explain working of Neural networks?

Ans.

Neural networks are a type of machine learning algorithm inspired by the human brain's neural structure.

  • Neural networks consist of layers of interconnected nodes (neurons) that process input data and pass it through activation functions.

  • They use weights to adjust the strength of connections between neurons during training.

  • Neural networks are capable of learning complex patterns and relationships in data, making them suitable for tasks like image recognition and natural langua...read more

Q91. What is linear and logistics.?

Ans.

Linear regression is a statistical method to model the relationship between a dependent variable and one or more independent variables. Logistic regression is used to model the probability of a binary outcome.

  • Linear regression is used for predicting continuous outcomes, while logistic regression is used for predicting binary outcomes.

  • In linear regression, the relationship between the independent and dependent variables is assumed to be linear, while in logistic regression, th...read more

Q92. Are u available for 3 months

Ans.

Yes, I am available for 3 months.

  • Yes, I am available for the entire duration of 3 months.

  • I have no prior commitments that would prevent me from completing the internship.

  • I am eager to dedicate my time and effort to the internship.

Q93. Explain difference between boosting algorithms

Ans.

Boosting algorithms are ensemble learning techniques that combine multiple weak learners to create a strong learner.

  • Boosting algorithms train models sequentially, with each model correcting errors made by the previous one.

  • Examples of boosting algorithms include AdaBoost, Gradient Boosting, and XGBoost.

  • AdaBoost adjusts the weights of incorrectly classified instances, Gradient Boosting fits new models to the residuals of the previous model, and XGBoost uses a more regularized m...read more

Q94. Importance of feature engineering.

Ans.

Feature engineering is crucial in data science as it involves selecting, transforming, and creating new features to improve model performance.

  • Feature engineering helps in improving model accuracy by providing relevant and meaningful input variables.

  • It involves techniques like one-hot encoding, scaling, normalization, and creating interaction terms.

  • Feature engineering can help in reducing overfitting and improving model interpretability.

  • Examples include creating new features f...read more

Q95. 2nd highest number from an array

Ans.

Find the 2nd highest number in an array of strings.

  • Convert the array of strings to an array of integers for comparison.

  • Sort the array in descending order to easily find the 2nd highest number.

  • Return the element at index 1 as the 2nd highest number.

Q96. Difference between KNN and K Means

Ans.

KNN is a supervised learning algorithm used for classification and regression, while K Means is an unsupervised clustering algorithm.

  • KNN stands for K-Nearest Neighbors and assigns a class label based on majority voting of its k-nearest neighbors.

  • K Means is a clustering algorithm that partitions data into k clusters based on similarity.

  • KNN requires labeled data for training, while K Means does not need labeled data.

  • KNN is a lazy learner as it does not learn a discriminative fu...read more

Q97. What is Bias In ML?

Ans.

Bias in ML refers to the systematic error in a model's predictions, leading to inaccurate results.

  • Bias is the algorithm's tendency to consistently learn the wrong thing by not taking all factors into account.

  • It can result from the data used to train the model being unrepresentative or skewed.

  • Bias can lead to unfair or discriminatory outcomes, especially in sensitive areas like hiring or lending decisions.

  • Examples include gender bias in resume screening algorithms or racial bi...read more

Q98. What is linear regression?

Ans.

Linear regression is a statistical method used to model the relationship between a dependent variable and one or more independent variables.

  • Linear regression aims to find the best-fitting straight line that describes the relationship between the variables.

  • It is commonly used for predicting future values based on past data.

  • The equation for a simple linear regression model is y = mx + b, where y is the dependent variable, x is the independent variable, m is the slope, and b is ...read more

Q99. What is supervised ML?

Ans.

Supervised ML is a type of machine learning where the model is trained on labeled data to make predictions or decisions.

  • Supervised ML requires a dataset with input variables and corresponding output labels.

  • The model learns from the labeled data to make predictions on new, unseen data.

  • Examples include classification tasks like spam detection or regression tasks like predicting house prices.

Q100. Python build in data types

Ans.

Python has several built-in data types including numeric, sequence, mapping, and set types.

  • Numeric types include integers, floats, and complex numbers.

  • Sequence types include lists, tuples, and strings.

  • Mapping types include dictionaries.

  • Set types include sets and frozensets.

  • Each data type has its own set of methods and operations.

  • Examples: int(5), float(3.14), complex(2+3j), list([1,2,3]), tuple((1,2,3)), str('hello'), dict({'key': 'value'}), set({1,2,3}), frozenset({4,5,6})

Previous
1
2
3
Next
Interview Tips & Stories
Ace your next interview with expert advice and inspiring stories

Interview experiences of popular companies

2.9
 • 110 Interviews
3.3
 • 32 Interviews
4.0
 • 27 Interviews
4.2
 • 26 Interviews
2.4
 • 17 Interviews
View all

Calculate your in-hand salary

Confused about how your in-hand salary is calculated? Enter your annual salary (CTC) and get your in-hand salary

Recently Viewed
INTERVIEWS
Golkonda Resorts and Spa
No Interviews
DESIGNATION
SALARIES
Blinkit
DESIGNATION
INTERVIEWS
Flip Robo Technologies
No Interviews
INTERVIEWS
Inland World Logistics
No Interviews
SALARIES
Accenture
INTERVIEWS
Teva Pharmaceuticals
No Interviews
SALARIES
Cognizant
SALARIES
Capgemini
Data Science Intern Interview Questions
Share an Interview
Stay ahead in your career. Get AmbitionBox app
qr-code
Helping over 1 Crore job seekers every month in choosing their right fit company
65 L+

Reviews

4 L+

Interviews

4 Cr+

Salaries

1 Cr+

Users/Month

Contribute to help millions

Made with ❤️ in India. Trademarks belong to their respective owners. All rights reserved © 2024 Info Edge (India) Ltd.

Follow us
  • Youtube
  • Instagram
  • LinkedIn
  • Facebook
  • Twitter