01
Type I vs Type II error?
Show answer
Type I = false positive (rejecting a true null), probability α. Type II = false negative (missing a real effect), probability β. Power = 1 − β.
Tata Elxsi Data Science Interview Questions & Answers
Curated interview practice questions with answers. These are practice scenarios, not a verified list of past interview questions.
About Tata Elxsi hiring for Data Science roles
Tata Elxsi is a Tata Group design and technology services company that works on product engineering for the automotive, media and communications, and healthcare industries. Its teams build embedded software, set-top box and streaming solutions, medical device software and user experience designs. In India it hires software, embedded, testing and design engineers, with a notable development centre in Thiruvananthapuram's Technopark.
For Data Science roles, this Tata Elxsi practice set focuses most on Deep Learning and NLP (7), Statistics and Probability (5), Python for Data Science (5), Generative AI and LLMs (4). It has 21 easy, 18 medium, 1 hard questions, so you can start easy and work up to the harder ones.
- Company type
- IT services
- Headquarters
- Bengaluru, India
- Main India offices
- Bengaluru, Thiruvananthapuram, Chennai, Pune
Tata Elxsi Data Science interview process
- Online assessment (aptitude + technical)
- Technical interview
- Managerial round
- HR round
Typical pattern based on public candidate experiences. Rounds vary by role, team and year.
Solved for Tata ElxsiStart practicing
3 QUESTIONS FREESign up to unlock the full question bank and track your progress.Unlock every question and answer, then continue practising company-wise and package-wise.
3 questions free Unlock the rest in seconds
02
Why is cross-entropy preferred over MSE for classification in neural networks?
Show answer
Cross-entropy measures how far predicted probabilities are from the true class and strongly penalises confident wrong predictions. With a softmax or sigmoid output, it gives large, useful gradients when the model is wrong. MSE with sigmoid outputs gives very small gradients when predictions saturate, so learning slows down. Use binary cross-entropy for two classes, categorical cross-entropy for many classes, and MSE for regression targets.
03
What is a system prompt in an LLM application?
Show answer
A system prompt is the instruction message placed before user messages that sets the model's role, tone, rules and output format, for example 'You are a support assistant; answer only from the provided policy and reply in JSON'. It shapes every response in the conversation. Keep it clear and specific, version it like code, and do not rely on it alone for security, since users can try to override it through prompt injection.
04
What is recursive feature elimination?
Show answer
Recursive feature elimination trains a model, ranks features by importance or coefficient size, removes the weakest ones, and repeats until the desired number remains. RFECV picks the number of features using cross-validation. It considers features together rather than one at a time. The downsides are high compute cost on large data and unstable results when features are correlated, so check stability across folds.
05
How do you handle missing values?
Show answer
First understand why data is missing. Then drop rows or columns with too many nulls, impute with mean/median/mode or a model (KNN), add a 'was_missing' flag, and fit imputers on training data only.
06
What is the difference between stemming and lemmatisation?
Show answer
Both reduce words to a base form. Stemming chops suffixes using rules, so studies becomes studi; it is fast but can produce non-words. Lemmatisation uses vocabulary and grammar to return the real dictionary form, so studies becomes study and better becomes good. Lemmatisation is more accurate but slower. With modern transformer models, neither is usually needed because subword tokenisers handle word forms.
07
What is the bias–variance trade-off?
Show answer
Bias is error from overly simple assumptions (underfitting). Variance is sensitivity to the training data (overfitting). More model complexity lowers bias but raises variance — aim for the lowest total error using cross-validation and regularization.
08
Write a Dockerfile for a Python model API.
Show answer
FROM python:3.11-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY app/ ./app
COPY model.joblib .
EXPOSE 8000
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
09
Write SQL to find the top 3 products by revenue in each category.
Show answer
WITH rev AS (
SELECT category, product_id, SUM(price * qty) AS revenue
FROM order_items
GROUP BY category, product_id
), ranked AS (
SELECT *, ROW_NUMBER() OVER (PARTITION BY category ORDER BY revenue DESC) AS rn
FROM rev
)
SELECT category, product_id, revenue
FROM ranked
WHERE rn <= 3;
10
Explain the basic idea of an ARIMA model.
Show answer
ARIMA models a time series using three parts. AR, autoregressive, uses past values of the series. I, integrated, differences the series d times to remove trend and make it stationary. MA, moving average, uses past forecast errors. You choose p, d and q using ACF and PACF plots or information criteria like AIC. SARIMA adds seasonal terms. ARIMA works well for single, fairly stable series but struggles with many external drivers.
11
Write torchvision transforms for training and validation of an image classifier using ImageNet normalisation.
Show answer
from torchvision import transforms as T
mean, std = [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]
train_tf = T.Compose([
T.RandomResizedCrop(224),
T.RandomHorizontalFlip(),
T.ColorJitter(0.2, 0.2, 0.2),
T.ToTensor(),
T.Normalize(mean, std),
])
val_tf = T.Compose([
T.Resize(256), T.CenterCrop(224),
T.ToTensor(), T.Normalize(mean, std),
])
12
What is data leakage?
Show answer
Information from outside the training window, such as future data or test statistics, enters training and inflates performance. Split first, then fit scalers and encoders on training data only.
13
How do you make a machine learning experiment reproducible?
Show answer
Version the code with Git, the data with a tool like DVC or dated snapshots, and the environment with pinned requirements or Docker. Set random seeds for every library. Log parameters, metrics and the exact data version for each run with a tracker like MLflow. Keep preprocessing inside a pipeline rather than manual notebook steps. Then anyone should be able to rebuild the same model from a commit and a data version.
14
Why are NumPy arrays faster than Python lists?
Show answer
They store same-type values in contiguous memory and run vectorised operations in compiled C, avoiding Python loop overhead and per-object type checks.
15
Write Pandas code to encode hour of day as a cyclical feature.
Show answer
import numpy as np
# hour 23 and hour 0 should be close, so use sin and cos
df['hour_sin'] = np.sin(2 * np.pi * df['hour'] / 24)
df['hour_cos'] = np.cos(2 * np.pi * df['hour'] / 24)
16
What is a confusion matrix?
Show answer
A table of true positives, false positives, true negatives and false negatives from which accuracy, precision, recall and F1 are calculated.
17
Pearson vs Spearman correlation?
Show answer
Pearson measures linear relationships on continuous data; Spearman uses ranks, so it captures monotonic relationships and is less sensitive to outliers.
18
What is a baseline model and why should you build one first?
Show answer
A baseline is the simplest reasonable prediction, such as predicting the most common class, last week's value or a basic logistic regression. It sets the minimum score any real model must beat. Without it, a 75 percent accuracy can look good when predicting the majority class already gives 80 percent. Baselines also catch pipeline bugs early and show whether extra complexity is worth it.
19
What is an A/A test and why would you run one?
Show answer
In an A/A test both groups get the identical experience. Since there is no real difference, results should be significant only about 5 percent of the time at alpha 0.05. Running A/A tests validates your experimentation platform: it catches broken randomisation, logging bugs, sample ratio problems and metrics whose variance is wrongly estimated. Teams often run them when launching a new platform or a new metric.
20
What is the difference between a base model and an instruction-tuned model?
Show answer
A base model is trained only to predict the next token on large text, so it continues text rather than following requests. An instruction-tuned model is further trained on instruction and answer pairs, and often preference data, so it follows prompts, answers questions and behaves like an assistant. For apps you usually use instruction-tuned or chat models. Base models are mainly starting points for custom fine-tuning.
21
Write pytest unit tests for a feature function that computes days since last purchase.
Show answer
import pandas as pd
from features import days_since_last_purchase
def test_basic_case():
df = pd.DataFrame({'customer_id': [1, 1], 'order_date': pd.to_datetime(['2026-01-01', '2026-01-10'])})
out = days_since_last_purchase(df, as_of='2026-01-15')
assert out.loc[1] == 5
def test_no_future_orders_used():
df = pd.DataFrame({'customer_id': [1], 'order_date': pd.to_datetime(['2026-02-01'])})
out = days_since_last_purchase(df, as_of='2026-01-15')
assert out.empty
22
What is the Global Interpreter Lock (GIL)?
Show answer
A mutex in CPython that lets only one thread execute Python bytecode at a time. Use multiprocessing for CPU-bound work and threads or asyncio for I/O-bound work.
23
Your daily sales forecast badly misses the Diwali spike every year. How do you fix it?
Show answer
The model is treating Diwali as noise because the festival moves on the calendar and a fixed yearly seasonality does not align. Add explicit holiday features: a flag for Diwali and a few days before and after, since buying starts early. Include other regional festivals and sale events too. Models like Prophet or gradient boosting with holiday features handle this well. Then backtest specifically on past festive periods to confirm the fix.
24
What is the difference between a one-tailed and a two-tailed test?
Show answer
A two-tailed test checks for a difference in either direction, for example whether a new page changes conversion up or down. A one-tailed test checks only one direction, such as whether it increases conversion. One-tailed tests have more power for that direction but ignore harm in the other direction. In most product experiments a two-tailed test is the safer default unless the direction was fixed before seeing data.
25
How does dropout work?
Show answer
During training it randomly switches off a fraction of neurons so the network cannot depend on any single unit, acting as a regulariser against overfitting.
26
What is named entity recognition?
Show answer
Named entity recognition finds and labels spans of text such as person names, organisations, locations, dates and amounts. For example, in an invoice email it can pull out the vendor, invoice number and total. It is usually framed as token classification with BIO tags. spaCy and fine-tuned transformer models are common tools. Domain-specific entities, like medicine names, usually need custom labelled training data.
27
What is a time series and how is it different from ordinary tabular data?
Show answer
A time series is a sequence of observations recorded at ordered time steps, such as daily sales or hourly website traffic. Unlike ordinary tabular data, rows are not independent: today's value depends on yesterday's, and the order cannot be shuffled. This changes everything downstream. You must split train and test by time, build features only from the past, and check for trend and seasonality before choosing a model.
28
Write Pandas code to read a large CSV in chunks and compute total sales per city.
Show answer
# process 1 million rows at a time
import pandas as pd
totals = {}
for chunk in pd.read_csv('sales.csv', usecols=['city', 'amount'], chunksize=1_000_000):
part = chunk.groupby('city')['amount'].sum()
for city, amt in part.items():
totals[city] = totals.get(city, 0) + amt
result = pd.Series(totals).sort_values(ascending=False)
29
What are Python's main built-in data types?
Show answer
int, float, complex, bool, str, list, tuple, set, dict and NoneType. Mutable ones are list, set and dict; the others are immutable.
30
How is an image represented for a deep learning model?
Show answer
An image is a numeric array of height by width by channels, where a colour image has three channels, usually RGB, with pixel values from 0 to 255. Libraries differ: OpenCV loads BGR in HWC order, while PyTorch expects tensors in CHW order with a batch dimension in front. Before training you convert to float, scale to 0-1 and normalise with the mean and standard deviation used by the pretrained model.
31
What do temperature and top-p control in LLM generation?
Show answer
Both control randomness when the model picks the next token. Temperature scales the probabilities: low values like 0 to 0.3 make output focused and repeatable, high values make it more varied and creative. Top-p, nucleus sampling, keeps only the smallest set of tokens whose probabilities add up to p, such as 0.9, and samples from them. For extraction and classification use low temperature; for brainstorming use higher values.
32
What is the receptive field of a neuron in a CNN?
Show answer
The receptive field is the region of the input image that can influence one activation. Early layers see small patches like edges, and deeper layers see larger regions, enabling recognition of whole objects. It grows with kernel size, depth, stride and pooling, and dilated convolutions increase it without extra parameters. If the receptive field is smaller than the objects you care about, the network cannot capture their full context.
33
Explain the chi-square test.
Show answer
It checks whether observed category counts differ from expected counts, used for independence between two categorical variables and for goodness of fit.
34
Write SQL to compute users, conversions and conversion rate for each experiment variant.
Show answer
SELECT
a.variant,
COUNT(DISTINCT a.user_id) AS users,
COUNT(DISTINCT o.user_id) AS converters,
ROUND(COUNT(DISTINCT o.user_id) * 1.0
/ COUNT(DISTINCT a.user_id), 4) AS conv_rate
FROM assignments a
LEFT JOIN orders o
ON o.user_id = a.user_id
AND o.created_at >= a.assigned_at
WHERE a.experiment_id = 'checkout_v2'
GROUP BY a.variant;
35
What is an autoencoder and what is it used for?
Show answer
A network that compresses inputs into a small latent code and reconstructs them; used for denoising, dimensionality reduction and anomaly detection.
36
What is subword tokenisation like BPE or WordPiece?
Show answer
Subword tokenisers split text into frequent pieces between characters and full words. Byte Pair Encoding starts from characters and repeatedly merges the most frequent pairs. WordPiece, used by BERT, is similar but chooses merges by likelihood. Rare words like unhappiness become un, happi, ness, so there are no unknown words and the vocabulary stays around 30,000 to 100,000. Token counts also decide LLM cost and context use.
37
Write Python code to compute a 95% bootstrap confidence interval for the mean.
Show answer
import numpy as np
def bootstrap_ci(x, n_boot=10000, seed=42):
rng = np.random.default_rng(seed)
x = np.asarray(x)
means = [rng.choice(x, size=len(x), replace=True).mean() for _ in range(n_boot)]
return np.percentile(means, [2.5, 97.5])
print(bootstrap_ci([12, 15, 9, 20, 14, 11, 18]))
38
Your LLM gives different summaries for the same document on different runs, but auditors need consistent output. What do you do?
Show answer
Set temperature to zero or near zero and fix other sampling settings, and use a seed where the API supports it, though outputs may still vary slightly. Pin the exact model version. Use a structured output format with fixed fields, and reduce ambiguity in the prompt. Cache and store each generated output with its inputs and version, so the stored result, not a regeneration, is what auditors see.
39
What is pooling in a CNN and why is it used?
Show answer
Pooling downsamples a feature map by summarising small regions. Max pooling keeps the largest value in each window, such as 2x2, and average pooling keeps the mean. It reduces computation, enlarges the receptive field of later layers and gives a little tolerance to small shifts. Many modern networks replace pooling with strided convolutions, but global average pooling before the classifier head is still very common.
40
Write Keras code for a small binary classifier on tabular data.
Show answer
from tensorflow import keras
model = keras.Sequential([
keras.layers.Input(shape=(X_train.shape[1],)),
keras.layers.Dense(64, activation='relu'),
keras.layers.Dropout(0.3),
keras.layers.Dense(1, activation='sigmoid')
])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['AUC'])
model.fit(X_train, y_train, validation_split=0.2, epochs=20, batch_size=64)
Tips to crack the Tata Elxsi Data Science interview
- Revise C, C++ or Python fundamentals along with operating systems and networking basics for embedded and media engineering roles.
- Prepare a crisp walkthrough of your best project, focusing on the problem, your contribution and what you would improve now.
- Read about Tata Elxsi's work in automotive software, video streaming and medical devices to show real interest in its domains.
- Keep a one-minute story ready for every project on your CV: problem, your part, tools, result.
- Practise the hard questions on this page aloud; Tata Elxsi interviewers usually ask follow-ups on your first answer.
Frequently asked questions
How many rounds are there in the Tata Elxsi Data Science interview?
Candidates usually go through 4 stages: Online assessment (aptitude + technical); Technical interview; Managerial round; HR round. The exact rounds change with the role, team, location and your experience, so confirm the process with the recruiter.
Which topics should I prepare for the Tata Elxsi Data Science interview?
This practice set leans on Deep Learning and NLP (7), Statistics and Probability (5), Python for Data Science (5), Generative AI and LLMs (4). Revise those first, then practise explaining one or two of your own projects end to end, because most Tata Elxsi interviewers ask you to walk through real work.
Are these the exact questions asked at Tata Elxsi?
No. These are curated practice questions that match the skills and difficulty usually tested in it services interviews like Tata Elxsi's. They are not a leaked or verified list of past questions.
Where does Tata Elxsi hire Data Science professionals in India?
Tata Elxsi has large teams in Bengaluru, Thiruvananthapuram, Chennai, Pune. Openings and locations change often, so check the Tata Elxsi careers page and filter by city and experience.
Data Science questions for similar companies
IT services
Cognizant
Data Science interview questions
Chennai, Bengaluru, Pune +2
View questionsIT services
EPAM Systems
Data Science interview questions
Hyderabad, Bengaluru, Pune +2
View questionsIT services
TCS
Data Science interview questions
Mumbai, Chennai, Pune +2
View questionsIT services
L&T Technology Services
Data Science interview questions
Vadodara, Bengaluru, Chennai +2
View questionsIT services
Infosys
Data Science interview questions
Bengaluru, Mysuru, Pune +2
View questionsIT services
Capgemini
Data Science interview questions
Mumbai, Bengaluru, Pune +2
View questionsMore ways to practise
Company-wise Data Science questionsPackage-wise Data Science questionsExperience-wise Data Science questionsRole-wise Data Science questionsCity-wise Data Science questionsMost asked Data Science questionsScenario-based questionsPractical / hands-on questionsHR & behavioural questionsData Science mock interviewOnline assessment questionsTechnical round questionsManagerial round questionsData Science topic sheets