Filter interviews by
I applied via Naukri.com and was interviewed before Jul 2021. There were 2 interview rounds.
LSTM is a type of recurrent neural network that can remember previous inputs. BiLSTM is a variant that processes input in both directions.
LSTM stands for Long Short-Term Memory
LSTM can remember long-term dependencies in data
BiLSTM processes input in both forward and backward directions
BiLSTM is useful for tasks such as named entity recognition and sentiment analysis
Top trending discussions
I appeared for an interview in Apr 2025, where I was asked the following questions.
Avoiding underfitting and overfitting involves techniques like regularization, cross-validation, and proper model selection.
Use cross-validation to assess model performance on unseen data, helping to identify overfitting.
Implement regularization techniques (L1, L2) to penalize overly complex models.
Choose the right model complexity; simpler models can prevent overfitting.
Increase training data to provide more examples ...
Linear regression can be used for forecasting, but its effectiveness depends on data patterns and relationships.
Linear regression assumes a linear relationship between input and output variables.
If the data shows a consistent trend, linear regression can provide reasonable forecasts.
Example: Predicting tomorrow's temperature based on historical temperature data.
However, it may not capture complex patterns or seasonalit...
Rotate a square matrix 90 degrees clockwise 'n' times efficiently.
A 90-degree clockwise rotation can be achieved by transposing the matrix and then reversing each row.
Example: For matrix [[1, 2], [3, 4]], after one rotation it becomes [[3, 1], [4, 2]].
To rotate 'n' times, calculate effective rotations as n % 4 since every 4 rotations return the matrix to its original state.
If n = 1, rotate once; if n = 2, rotate twice ...
Build a simple cat and dog image classifier
I appeared for an interview in Mar 2025, where I was asked the following questions.
I appeared for an interview in Sep 2024, where I was asked the following questions.
SQL window functions allow for advanced data analysis by performing calculations across a set of table rows related to the current row.
Window functions operate on a set of rows defined by an OVER() clause.
Common window functions include ROW_NUMBER(), RANK(), and SUM().
Example: SELECT employee_id, salary, RANK() OVER (ORDER BY salary DESC) AS salary_rank FROM employees;
Window functions can be used for running totals, mo...
Simple mediam DSA style questions around ML
Calculate year-over-year (YoY) rates using Pandas groupby for a specific column in a dataset.
Use the Pandas 'groupby' method to group data by the desired category (e.g., 'year').
Apply the 'pct_change()' function to calculate the percentage change between years.
Example: df.groupby('year')['sales'].sum().pct_change() to get YoY sales growth.
Ensure the data is sorted by year before applying the calculation for accurate re...
Case study design oka6y
A case study involves analyzing a specific situation to derive insights and solutions using data science techniques.
Define the problem clearly: Identify the key issues to address.
Collect relevant data: Gather data from various sources, ensuring quality and relevance.
Analyze the data: Use statistical methods and machine learning to uncover patterns.
Draw insights: Interpret the results to provide actionable recommendatio...
I appeared for an interview in Nov 2024, where I was asked the following questions.
Customer Success Manager
8
salaries
| ₹5.7 L/yr - ₹12.9 L/yr |
Software Engineer
7
salaries
| ₹5 L/yr - ₹11.7 L/yr |
Software Developer
4
salaries
| ₹6.6 L/yr - ₹13 L/yr |
Data Scientist
4
salaries
| ₹6 L/yr - ₹15 L/yr |
Client Engagement Manager
4
salaries
| ₹8.5 L/yr - ₹9.4 L/yr |
Udaan
Swiggy
CARS24
BlackBuck