Filter interviews by
I applied via Approached by Company and was interviewed in Sep 2022. There were 4 interview rounds.
Developed a machine learning model to predict customer churn in a telecommunications company.
Collected and preprocessed customer data including demographics, usage patterns, and service history.
Performed exploratory data analysis to identify key features and patterns.
Built and trained a classification model using a combination of logistic regression and random forest algorithms.
Evaluated the model's performance using m...
Multivariate analysis is a statistical technique used to analyze data with multiple variables.
It involves examining the relationships between multiple variables to identify patterns and trends.
Common techniques include principal component analysis, factor analysis, and cluster analysis.
Multivariate analysis is used in various fields such as finance, marketing, and social sciences.
Example: A marketing team may use multi...
Multivariate time series is a collection of time series data where multiple variables are observed simultaneously over time.
Multivariate time series models are used to analyze and forecast complex systems with multiple interacting variables.
Common models include Vector Autoregression (VAR), Vector Error Correction Model (VECM), and Dynamic Factor Models (DFM).
Model selection and parameter estimation can be challenging ...
No, it is not always important to apply ML algorithms to solve any statistical problem.
ML algorithms may not be necessary for simple statistical problems
ML algorithms require large amounts of data and computing power
ML algorithms may not always provide the most interpretable results
Statistical models may be more appropriate for certain types of data
ML algorithms should be used when they provide a clear advantage over t
Anomaly detection is the process of identifying data points that deviate from the expected pattern.
Anomaly detection is used in various fields such as finance, cybersecurity, and manufacturing.
It can be done using statistical methods, machine learning algorithms, or a combination of both.
Some common techniques for anomaly detection include clustering, classification, and time series analysis.
Examples of anomalies inclu...
Event Detection is the process of identifying and extracting meaningful events from data streams.
It involves analyzing data in real-time to detect patterns and anomalies
It is commonly used in fields such as finance, social media, and security
Examples include detecting fraudulent transactions, identifying trending topics on Twitter, and detecting network intrusions
Gaussian Mixture Model is a probabilistic model used for clustering and density estimation.
GMM assumes that the data points are generated from a mixture of Gaussian distributions.
It estimates the parameters of these Gaussian distributions to cluster the data points.
An industrial example of GMM is in customer segmentation for targeted marketing.
GMM can also be used in anomaly detection and image segmentation.
GMM can be used to model normal behavior and identify anomalies based on low probability density.
GMM can be used to fit a model to the normal behavior of a system or process.
Anomalies can be identified as data points with low probability density under the GMM model.
The number of components in the GMM can be adjusted to balance between overfitting and underfitting.
GMM can be combined with other techniques such as PCA or...
GMM is more robust for Anomaly detection than Tukey's method of IQR or Z-Score method.
GMM can handle complex data distributions and can identify multiple anomalies.
Tukey's method and Z-Score method are limited to detecting anomalies in unimodal distributions.
GMM can also handle missing data points and outliers better than the other two methods.
GMM is robust to anomaly detection due to its ability to model complex data distributions.
GMM can model data distributions with multiple modes, making it more flexible than other methods.
It can also handle data with varying densities and shapes, making it suitable for detecting anomalies.
GMM uses a probabilistic approach to assign data points to different clusters, allowing it to identify outliers.
It can be used in uns...
Anomalies in Multivariate Time Series can be detected using statistical methods like PCA, clustering, and deep learning models.
Use Principal Component Analysis (PCA) to identify the most important features and detect anomalies in the residual errors.
Cluster the data points and identify the clusters with low density or high variance as anomalies.
Use deep learning models like LSTM or Autoencoder to learn the patterns in ...
Median is more robust to outliers than mean and mode.
Mean is sensitive to outliers as it takes into account all the values in the dataset.
Mode is not affected by outliers as it only considers the most frequent value.
Median is the middle value in a dataset and is less affected by outliers as it is not influenced by extreme values.
For example, if we have a dataset of salaries and one person earns a million dollars, the m...
Mahalanobis Distance is a measure of distance between a point and a distribution.
It takes into account the covariance between variables.
It is used in multivariate analysis and classification problems.
Assumes that the data is normally distributed and has equal covariance matrices.
It is sensitive to outliers and can be used to detect them.
Euclidean distance measures straight line distance between two points while Mahalanobis distance considers variance and covariance of the data.
Euclidean distance is the most common distance metric used in machine learning.
Mahalanobis distance is used when the data has different variances and covariances.
Mahalanobis distance is more robust to outliers than Euclidean distance.
Mahalanobis distance is used in clustering, c...
Yes, Local Outlier Factor (LOF) is a non-parametric anomaly detection method that does not require normality assumptions.
LOF is based on the idea that anomalies are located in less dense areas than their neighbors
LOF calculates the local density of each data point and compares it to the densities of its neighbors
LOF assigns an anomaly score to each data point based on how much its local density differs from the densiti
Analytical, innovative, detail-oriented
Analytical: I have a strong ability to analyze complex data and extract meaningful insights.
Innovative: I constantly seek new and creative approaches to problem-solving and developing data-driven solutions.
Detail-oriented: I pay close attention to details to ensure accuracy and precision in my work.
My hobby is photography because it allows me to capture and express the beauty of the world.
Photography allows me to explore and appreciate the details in my surroundings.
It helps me to see things from different perspectives and enhances my creativity.
I enjoy experimenting with different techniques and capturing unique moments.
Photography also serves as a form of relaxation and mindfulness for me.
I score myself highly in interpersonal skills because I have a proven track record of effectively communicating and collaborating with diverse teams.
I have excellent communication skills, both verbal and written.
I am able to listen actively and empathetically to others.
I can effectively convey complex technical concepts to non-technical stakeholders.
I have experience working in cross-functional teams and fostering posi...
I have a strong background in data science and leadership skills necessary for the role of Principal Data Scientist.
Extensive experience in data analysis and modeling
Proven track record of leading successful data science projects
Strong knowledge of machine learning algorithms and statistical techniques
Ability to communicate complex findings to both technical and non-technical stakeholders
Experience in managing and ment...
Top trending discussions
Static class and static constructor in C#
Static class can only contain static members and cannot be instantiated
Static constructor is called only once when the class is first accessed
Static constructor is used to initialize static members of the class
Example: Math class in C# is a static class
Example: static constructor can be used to initialize a static variable with a value
Performance improvement in Angular app
Use lazy loading to load modules on demand
Optimize change detection strategy
Use trackBy function in ngFor loops
Minimize DOM manipulation
Use AOT compilation
Implement server-side rendering
Use web workers for heavy computations
Use caching for frequently accessed data
Performing web application penetration testing on a website with firewall enabled.
Identify the type of firewall and its configuration
Perform reconnaissance to gather information about the target
Identify vulnerabilities and exploit them
Use tools like Burp Suite, Nmap, and Metasploit
Test for common web application vulnerabilities like SQL injection and cross-site scripting
Document findings and provide recommendations for
I appeared for an interview before Dec 2020.
Round duration - 120 Minutes
Round difficulty - Medium
Ninja, a new member of the FBI, has acquired some 'SECRET_INFORMATION' that he needs to share with his team. To ensure security against hackers, Ninja dec...
The task is to encode and decode 'SECRET_INFORMATION' for security purposes and determine if the transmission was successful.
Read the number of test cases 'T'
For each test case, encode the 'SECRET_INFORMATION' and then decode it
Compare the decoded string with the original 'SECRET_INFORMATION'
Print 'Transmission successful' if they match, else print 'Transmission failed'
Round duration - 60 Minutes
Round difficulty - Medium
Given an array Arr
consisting of N integers, your task is to find the equilibrium index of the array.
An index is considered as an equilibrium index if the sum of elem...
Find the equilibrium index of an array where sum of elements on left equals sum on right.
Iterate through the array and calculate prefix sum and suffix sum at each index.
Compare prefix sum and suffix sum to find equilibrium index.
Return the left-most equilibrium index or -1 if none found.
Round duration - 50 Minutes
Round difficulty - Easy
Tip 1 : Focus more on SQL
Tip 2 : Keep up with ongoing projects in the company
Tip 1 : Be honest about what you add.
Tip 2 : Don't forget to mention extra curriculars.
I applied via Naukri.com and was interviewed in Jan 2021. There were 4 interview rounds.
I applied via Naukri.com and was interviewed in Jan 2021. There was 1 interview round.
Steps for Azure migration from onprem to cloud and Hyper V migration using VMWARE tool.
Assess on-premises environment
Choose appropriate migration method
Prepare Azure environment
Migrate data and applications
Optimize and secure migrated resources
VMware tool used for migration: VMware vCenter Converter
Hyper-V migration can be done using Azure Site Recovery
I applied via Naukri.com and was interviewed in Mar 2021. There were 4 interview rounds.
Memory management is crucial for efficient application performance.
Memory allocation and deallocation should be done carefully to avoid memory leaks.
Unused memory should be released to prevent memory fragmentation.
Memory profiling tools can help identify memory-related issues.
Caching can improve performance by reducing the need for frequent memory allocation.
Examples: Java's garbage collector, C++'s smart pointers, iOS
I applied via Naukri.com and was interviewed in Jul 2021. There were 3 interview rounds.
I applied via Referral and was interviewed before Jan 2021. There were 3 interview rounds.
Some of the top questions asked at the Itobuz Technologies Principal Data Scientist interview -
based on 1 interview
Interview experience
Front end Developer
12
salaries
| ₹3 L/yr - ₹4.1 L/yr |
Senior Front end Developer
8
salaries
| ₹5.5 L/yr - ₹10 L/yr |
Software Developer
6
salaries
| ₹4.9 L/yr - ₹6.5 L/yr |
Web Developer
6
salaries
| ₹2.7 L/yr - ₹5.5 L/yr |
Backend Developer
5
salaries
| ₹4 L/yr - ₹5.3 L/yr |
TCS
Accenture
Wipro
Cognizant