Top 22 Data Science Interview Questions in 2022

July 6, 2022

There is nothing new in saying that data is gold. We all know this, every organization of every scale depends heavily on mining the data for generating growth and profit. And it is necessary for organizations today to keep a data science team in hand to handle complex data-related problems. 

Even on the job aspirants' side, opportunities in the field of data science are very lucrative and attract widespread attention. To help such candidates, this blog highlights the top 22 Data Science Interview questions that can come in handy while appearing for a data science job interview. 

Ques 1. What, in your opinion, accounts for Deep Learning's current surge in popularity?

Ans 1. Even though Deep Learning has been around for a while, the biggest advances in the field have only recently been made. There are two basic causes for this:  the expansion of data produced from a variety of sources and the increasing amount of hardware needed to run these models, particularly Cloud GPU services. 

Since GPUs are so much quicker than CPUs, we can now create deeper and larger deep learning models much more quickly than we could in the past.

Ques 2. Why Is Tensorflow the Most Popular Deep Learning Library?

Ans 2. Tensorflow has a faster compilation time than other Deep Learning libraries like Keras and Torch and has both C++ and Python APIs, making it simpler to work with. Tensorflow is compatible with both CPU and GPU-based computer systems.

Ques 3. What is sampling's main benefit? What procedures are employed in sampling? 

Ans 3. Sampling is the process of choosing the group from which you will actually collect data for your study. For instance, you could interview a sample of 100 students if you were examining the viewpoints of students at your university. This saves both time and resources while conducting research. 

There exist two categories of sampling techniques:

  1. Probability sampling: Random selection is a key component of probability sampling, which enables you to draw robust statistical conclusions about the entire group. Clustered sampling, Simple random sampling, and Stratified sampling are a few examples of this category. 
  2. Non-probability sampling: This technique entails non-random selection based on practicality or other factors, making it simple to gather data. For example: Quota sampling, Convenience sampling, snowball sampling, etc.

Ques 4. What does variance in data science mean?

Ans 4. Variance is a sort of inaccuracy that develops in a Data Science model as it becomes overly complicated and learns features from data, along with any noise that may be present. Even though the data and underlying patterns and trends are relatively clear to spot, this type of inaccuracy can happen if the technique used to train the model is highly sophisticated. As a result, the model is extremely sensitive and does well on the training dataset but poorly on the testing dataset and on any other type of data. Variance typically results in overfitting and poor testing accuracy.

Ques 5.  What makes supervised and unsupervised learning different?

Ans 5. The use of labeled datasets distinguishes the machine learning strategy known as supervised learning. These datasets are intended to "supervise" or "train" algorithms to correctly classify data or forecast outcomes. Labeled inputs and outputs allow the model to monitor its precision and improve over time. When using data mining, supervised learning may be divided into two categories of issues: classification and regression. 

While unsupervised learning analyses and groups unlabeled data sets using machine learning techniques. These algorithms are referred to as "unsupervised" since they identify hidden patterns in data without the assistance of a person. Clustering, association, and dimensionality reduction are the three basic tasks that unsupervised learning models are utilized for.

Ques 6. What does bias in data science mean?

Ans 6. When an algorithm is used in a data science model, bias can happen because it is unable to fully capture the underlying patterns or trends in the data. In other words, this error happens when the algorithm creates a model based on simplistic assumptions since the input is too complex for it to comprehend. As a result, underfitting results in reduced accuracy. Regression algorithms like logistic and linear can result in substantial bias.

Ques 7. What exactly is dimensionality reduction?

Ans 7. The method of reducing the number of dimensions (fields) in a dataset involves making data and its field less redundant. Dimensionality reduction involves the removal of a few fields or columns from the dataset. But this is not carried out carelessly. In this method, the dimensions or fields are only removed after confirming that the remaining data will still be sufficient to briefly describe the related problems or can represent the whole data.

Ques 8. What are the popular libraries used in Data Science?

Ans 8.  Below are the most popular libraries used in Data Science-

-TensorFlow: Provides flawless library management for parallel computing.


-SciPy: Mostly used for manipulating data, solving multidimensional programming problems, and visualizing data using graphs and charts. 

-Matplotlib: Since it is free and open-source, it can be used in place of MATLAB, producing better results and using less memory. 

-Pytorch: Best for projects using Deep Neural Networks and Machine Learning methods. 

-Pandas: ETL (Extracting, Transforming, and Loading the datasets) capabilities are implemented in commercial applications using pandas.

Ques 9. Describe the operation of a recommender system?

Ans 9. Many consumer-facing, content-driven, online platforms use a recommender system to produce user-specific recommendations from a library of available information. Based on the users' behaviors on the site, these systems produce recommendations based on what they know about their preferences.

Imagine, for instance, that we have a movie streaming service that is comparable to Netflix or Amazon Prime. A user is said to enjoy watching action and horror films if they have already watched and enjoyed films in these genres. In that situation, it would be preferable to suggest these movies to this specific user. These suggestions can also be produced using the content that individuals with similar tastes enjoy watching.

Ques 10. Describe Normal Distribution?

Ans 10. A visualization tool called data distribution can be used to examine how data is dispersed or disseminated. Different methods can be used to distribute data. For instance, there can be a bias to the left or right, or everything might be mixed up. 

Data, such as the mean, median, etc., can also be dispersed about a central value. This type of distribution, which resembles a bell-shaped curve, is unbiased in either the left or the right directions. The mean of this distribution is also the same as the median. A normal distribution is a name given to this type of distribution.

Ques 11.  What does a decision tree mean in Data Science?

Ans 11. A supervised learning approach called a decision tree is utilized for both classification and regression. As a result, the dependent variable in this situation can have either a numerical value or a categorical value. Each node in a decision tree represents a test on an attribute, each edge represents the result of that test, and each leaf node contains the class label.

Ques 12. A Boltzmann machine: What is it?

Ans 12. Boltzmann machines have a straightforward learning process that enables them to find intriguing features in the training data that represent intricate regularities. The main purpose of the Boltzmann machine is to optimize the weights and quantities for the given problem. In networks with numerous layers of feature detectors, the learning algorithm is quite sluggish. The "Restricted Boltzmann Machines" approach is quicker than the others because it only uses one layer of feature detectors.

Ques 13. What is an auto-encoder?

Ans 13. Simple learning networks called auto-encoders work to convert inputs into outputs as accurately as possible. This indicates that our goal is to have the output be as close to the input as feasible. Between the input and the output, we add a few layers, and the sizes of these layers are less than the input layer. The auto-encoder receives unlabelled input which is then encoded to reconstruct the input.

Ques 14. What is the role of the Activation Function?

Ans 14. The neural network is given non-linearity through the activation function, which enables it to learn more complex functions. Without it, the neural network could only learn linear functions, which are combinations of the data it receives in a linear fashion. An artificial neuron's activation function produces an output in response to inputs.

Ques 15. Describe what backpropagation is and how it works?

Ans 15. A multilayer neural network's training algorithm is backpropagation. By moving the error from one end of the network to all of its weights, this method enables the computation of the gradient to be done quickly. 

In Backpropagation, first training data is propagated forward then output and target are used to compute derivatives. To compute the derivative of an error with respect to output activation, backpropagation is done. Then in the end, using derivatives that have already been calculated as output weights are refreshed. 

Ques 16. How should outlier values be handled? 

Ans 16. Any graphical analysis technique, even univariate, can be used to detect outlier values. If there are only a few outlier values, each one can be evaluated separately, but if there are several, the values can be replaced with either the 99th or the 1st percentile values. 

The most typical method for handling outlier values is  to adjust the value so that it is inside a certain range or  just remove the value

Ques 17. What is Exploding and Vanishing Gradient?

Ans 17. Exploding Gradients are erroneous gradients that expand exponentially during the training of an RNN, aggregate, and lead to very large modifications to the weights of the neural network model. At their most extreme, weight values have the potential to overflow and produce NaN values. Because of exploding gradient, your model will suffer as a result, making it unable to benefit from your training set of data.

While in Vanishing Gradient your slope may get too narrow, which makes training challenging. Long training sessions, subpar performance, and low precision are the results of a vanishing gradient. 

Ques 18. What Sets Epoch, Batch, and Iteration Apart in Deep Learning?

Ans 18. 

-Epoch: One iteration of the complete dataset is represented by an epoch (everything put into the training model). 

-Batch: When we divide a dataset into multiple batches because we can't feed the complete dataset at once to the neural network, this is referred to as batching. 

-Iteration: An epoch should run 50 iterations if the input data contains 10,000 photos and the batch size is 200. (10,000 divided by 50).

Ques 19. Define Cost function?

Ans 19. The cost function, which is often known as "loss" or "error," is a metric for gauging how well your model performs. It is employed to calculate the output layer's error during backpropagation. In order to use it for the various training functions, we push that error backward through the neural network.

Ques 20. What is the repercussion of setting a wrong learning rate?

Ans 20. The model's training will advance very slowly if your learning rate is too low because we are just making minor weight updates. Before reaching the minimum point, there will be a need for several revisions. On the other hand, the loss function exhibits unwanted divergent behavior if the learning rate is set too high because weights are drastically updated. It could diverge or fail to converge respectively. 

Ques 21. How Often Does an Algorithm Need to Be Updated?

Ans 21. An algorithm has to be updated when: 

  • In order for the model to change as more data flows via the infrastructure 
  • The source of the underlying data is evolving. 
  • There is a non-stationarity instance. 
  • The algorithm is inefficient and produces inaccurate results.

Ques 22. How do you handle missing values in a dataset?

Ans 22. After finding the variables with missing values, the extent of the missing values is determined. If any patterns emerge, the analyst must focus on them since they may yield fascinating and valuable business insights. 

If no patterns are found, it is possible to ignore the missing numbers entirely or to impute them using mean or median values. a default value is being assigned, which can be the mean, minimum, or maximum value. Entering the data is crucial. 

If the variable is categorical, the default value is chosen. A default value is given to the missing variable. Give the mean value for a normal distribution if you have a distribution of data. 

Else you can also respond that you would drop the variable in place of processing the missing values if 80% of the values for a variable are missing.


Data Science is a very broad discipline that covers a variety of subjects, including Machine Learning, Deep Learning, Data Mining, Data Analysis, and Data Visualization. But most significantly, it is built on the foundation of mathematical ideas like Linear Algebra and Statistical analysis. 

So if you have an interview scheduled soon, don’t forget to brush up on your mathematical concepts with the coding and other practices.

Latest Blogs
This is a decorative image for: A Complete Guide To Customer Acquisition For Startups
October 18, 2022

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

  • Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

  • MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
  • CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.  
  • CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
  • Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

  • Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

  • Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels. 

  • Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

Reference Links

This is a decorative image for: Constructing 3D objects through Deep Learning
October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

  • Highly calibrated cameras that take a photograph of the image from various angles.
  • Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

  • Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

  • Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

  • Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

  • Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

  • Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

  • 3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
  • It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
  • They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
  • It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
  • It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website

Reference Links

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts
October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning   is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

  1. Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
  2. Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
  3. Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
  4. Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.  

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

This is a decorative image for: GAUDI: A Neural Architect for Immersive 3D Scene Generation
October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

  • The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
  • Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
  • GAUDI also removes GANs pathologies like mode collapse and improved GAN.
  • GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

  • Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
  • This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
  • The scenes are thus synthesized by interpolation within the hidden space.
  • The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
  • A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

Reference Links

Build on the most powerful infrastructure cloud

A vector illustration of a tech city using latest cloud technologies & infrastructure