Tower Research Capital Data Science Interview Questions & Answers
Curated interview practice questions with answers. These are practice scenarios, not a verified list of past interview questions.
About Tower Research Capital hiring for Data Science roles
Tower Research Capital is a quantitative trading firm that develops automated, high-frequency trading strategies across global markets. Its Gurugram office works on trading systems, low-latency software, infrastructure and quantitative research. It hires in India for software engineers, quantitative researchers and traders, with interviews that focus heavily on problem solving, probability and systems.
For Data Science roles, this Tower Research Capital practice set focuses most on Machine Learning (10), Feature Engineering (5), A/B Testing & Experimentation (4), MLOps and Model Deployment (4). It has 5 easy, 30 medium, 5 hard questions, so you can start easy and work up to the harder ones.
Company type
Fintech
Headquarters
New York, USA
Main India offices
Gurugram
Tower Research Capital Data Science interview process
Online assessment (coding + quant)
Technical round 1 (DSA)
Technical round 2 (C++ or systems)
Quant or probability round
HR round
Typical pattern based on public candidate experiences. Rounds vary by role, team and year.
Solved for Tower Research CapitalStart 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
01
Difference between a shallow copy and a deep copy?
A shallow copy duplicates the outer object but shares nested objects. A deep copy (copy.deepcopy) recursively duplicates everything, so changes to nested items do not leak.
02
What is the randomisation unit in an experiment, and why does it matter?
The randomisation unit is what you assign to variants: a user, a session, a device, a page view or even a city. Choosing user-level keeps each person's experience consistent and avoids contamination. The analysis unit should match the randomisation unit, because if you randomise by user but analyse by page view, observations are correlated and standard errors come out too small, producing false positives. Use the delta method or bootstrap when they differ.
03
Your dataset is highly imbalanced (2% positives). How do you handle it?
Use stratified splits, class weights, resampling (SMOTE or undersampling) and threshold tuning, and judge the model with PR-AUC or F1 instead of accuracy.
04
Tell me about a time your forecast was badly wrong. How did you handle it?
Situation: my weekly demand forecast under-predicted a category by 30 percent for a month. Task: explain the miss and stop it recurring. Action: I compared forecast and actuals by region and found a new distribution channel had launched that the model knew nothing about. I told the planning team quickly, added channel as a feature and set up a weekly error review. Result: error returned to normal and planners trusted the alerts.
05
Your manager asks whether collecting more training data will improve the model. How do you answer using a learning curve?
A learning curve plots training and validation scores against the size of the training set. If both scores are low and close, the model has high bias and needs more features or a more flexible model. If training is high but validation is much lower and the gap narrows as data grows, the model has high variance and more data will help. It tells you whether collecting more data is worth the cost.
It combines gradient boosting with regularisation, handling of missing values, parallel tree construction and speed optimisations, and it performs strongly on tabular data.
07
You need forecasts for 50,000 SKUs every week. Would you build one model per series or one global model?
One classical model per SKU is simple and interpretable but expensive to maintain, and it fails for short or sparse series. A global model, such as LightGBM trained on all SKUs with lags, calendar and product features, learns shared patterns and handles new items better. In practice I would use a global model as the main engine, keep statistical models for a few high-value series, and compare both in a rolling backtest.
08
Tell me about a time you had to deliver data under an urgent deadline.
Situation: the leadership team needed festive-sale numbers by city for a 9 am review, and the dashboard pipeline had failed overnight. Task: deliver accurate numbers in three hours. Action: I queried the raw orders tables directly, reused validated logic from the dashboard SQL, cross-checked totals with finance's daily figure and flagged two cities with partial data. Result: the review went ahead on time, and I later added pipeline failure alerts.
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.
10
What is statistical power and how can you increase it?
Power is the probability of detecting a real effect. Increase it with a larger sample, a bigger effect size, lower noise or a higher significance level.
11
Your sales forecast scores well in k-fold cross-validation but fails in production. What could be wrong with the validation?
Random k-fold mixes future and past rows, so the model trains on data from after the period it predicts. That leaks information and inflates scores. Use time-based splits instead: train on an expanding or rolling window and validate on the next period, like TimeSeriesSplit in scikit-learn. Leave a gap between train and validation when features use lagged values, so the test reflects real forecasting conditions.
12
Your forecast uses actual daily temperature as a feature and looks great in backtesting, but it performs worse in production. Why?
In backtesting you used the actual temperature for future days, which you will never know at forecast time. In production the model gets a weather forecast, which has its own error, so performance drops. This is a subtle form of leakage. Fix the backtest by using the weather forecast that was available on each forecast date, or lagged actuals, so offline results match what production can really achieve.
13
Write a prompt template for classifying customer support tickets.
System: You classify support tickets for an e-commerce company. Categories: payment, delivery, refund, account, other. Rules: choose exactly one category; if unsure, choose other; do not invent details. Return JSON with fields category and reason, reason under 20 words. Then two short examples showing a ticket and the expected JSON. User: Ticket: {ticket_text}. Keep the template fixed and test it on 100 labelled tickets before rollout.
Covariance shows the direction of a relationship but depends on units. Correlation is covariance scaled to −1…+1, so it shows direction and strength and is unit-free.
15
Write pytest unit tests for a feature function that computes days since last purchase.
A large language model is a neural network, usually a decoder-only transformer, trained on huge amounts of text to predict the next token. With billions of parameters and further instruction tuning, it can answer questions, summarise, write code and follow instructions. It does not look up facts; it generates likely text based on patterns learned in training, so it can be fluent but wrong. Data scientists use LLMs through APIs or open-weight models.
17
Halfway through a test you discover a bug that broke the treatment for Android users. What do you do?
Stop or pause the affected part, fix the bug and restart the test with fresh data, since mixing broken and fixed periods biases results. Do not simply drop Android users from analysis afterwards, because that can break randomisation balance if the bug affected behaviour or logging. Document the incident, and add pre-launch checks such as running the variant through QA on every platform and monitoring guardrails in the first hours.
18
Write Python code to calculate the sample size per group needed to detect a lift from 5 percent to 5.5 percent conversion.
This is domain shift: user photos have clutter, blur, poor lighting and odd angles that the model never saw. Collect and label a sample of real user photos and evaluate on them separately. Add augmentation for blur, noise, colour jitter, rotation and random crops, and fine-tune on a mix of studio and real images. Monitor accuracy on user photos in production, since that is the distribution that matters.
20
Write scikit-learn code to calibrate a gradient boosting classifier's probabilities and check the result.
This is training-serving skew. The feature might be computed from data that arrives later, like final order status. First confirm exactly when each feature is available in production. Rebuild the training set using point-in-time values, as they were at prediction time, or drop the feature. A feature store with point-in-time joins and the same feature code for training and serving prevents this. Expect offline scores to drop, but they become honest.
It projects data onto orthogonal directions of maximum variance to reduce dimensions, remove correlation and speed up models, at some cost of interpretability.
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.
24
How would you build a churn prediction model end to end?
Define churn and the prediction window, build behavioural features, split by time, train and compare models, evaluate with recall and lift, explain drivers and monitor drift after deployment.
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.
26
Your model performance degrades every few months. Would you retrain on a fixed schedule or based on triggers?
Scheduled retraining, like monthly, is simple and predictable but may be too late after a sudden change or wasteful when nothing changed. Trigger-based retraining runs when monitoring shows drift or a performance drop, which reacts faster but needs reliable monitoring. Many teams combine both: a regular schedule plus triggers for big shifts. Either way, a retrained model must pass the same evaluation gate before replacing the current one.
27
Write Python code to compute the haversine distance between customer and store locations.
The ROC curve plots true positive rate against false positive rate across thresholds. AUC is the probability that a random positive is ranked above a random negative; 0.5 is chance.
29
What is the minimum detectable effect (MDE) in experiment design?
The MDE is the smallest true effect your test can reliably detect given the sample size, baseline rate, significance level and power. If baseline conversion is 5 percent and your MDE is 10 percent relative, you can detect a move to 5.5 percent but will likely miss smaller lifts. Choose the MDE from business value: the smallest change worth shipping. A smaller MDE needs a much larger sample, roughly growing with one over MDE squared.
30
What is gradient descent and what does the learning rate do?
An optimisation method that updates weights in the opposite direction of the loss gradient. The learning rate sets the step size: too high and it diverges, too low and it is slow. Variants include SGD, mini-batch and Adam.
It lets a model weigh which input positions matter most for each output, computing weighted combinations of values from query-key similarity. It is the core of transformers.
32
How would you quickly build a sentiment analysis model for product reviews?
Step 1: collect and label a sample of reviews, checking class balance. Step 2: build a baseline with TF-IDF and logistic regression to get a quick benchmark. Step 3: fine-tune a small pretrained transformer such as DistilBERT for better accuracy, or use a multilingual model if reviews mix languages. Step 4: evaluate with F1 per class and read wrong predictions. Step 5: handle sarcasm and neutral reviews explicitly.
33
Write SQL to find the top 3 products by revenue in each category.
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;
34
What is DBSCAN and when is it better than K-means?
DBSCAN is a density-based clustering algorithm. It groups points that have at least min_samples neighbours within distance eps, and marks isolated points as noise. Unlike K-means, it does not need the number of clusters, finds clusters of any shape, and handles outliers. It struggles when clusters have very different densities and in high dimensions. It suits location data, like finding delivery hotspots from GPS points.
A DAG, directed acyclic graph, in Apache Airflow defines a workflow as tasks with dependencies, such as extract data, build features, train model and publish scores, in that order. Airflow schedules runs, retries failed tasks, passes run dates and shows status in a web UI. Acyclic means no task can loop back to an earlier one. Data scientists use it for scheduled training and batch scoring pipelines.
36
How do one-stage and two-stage object detectors differ?
Two-stage detectors, like Faster R-CNN, first propose candidate regions and then classify and refine each one, which gives strong accuracy, especially for small objects, but is slower. One-stage detectors, like YOLO and SSD, predict boxes and classes directly over a dense grid in a single pass, making them fast enough for real-time video. Modern one-stage models have closed most of the accuracy gap, so they dominate edge and video use cases.
37
How would you fine-tune a pretrained language model for classification?
Add a classification head, freeze or gradually unfreeze layers, use a small learning rate, train on labelled data with validation, and track F1 per class.
38
What is the difference between apply, map and applymap in Pandas?
map works element-wise on a Series, apply works on a Series or along a DataFrame axis, and applymap (now DataFrame.map) applies a function to every cell.
39
Write Pandas code to create lag and rolling features for each customer.
df = df.sort_values(['customer_id', 'month'])
g = df.groupby('customer_id')['spend']
df['spend_lag1'] = g.shift(1)
df['spend_lag3'] = g.shift(3)
# shift first so the current month is not included
df['spend_roll3_mean'] = g.transform(lambda s: s.shift(1).rolling(3).mean())
40
After one-hot encoding you have 2,000 features and training is slow. What do you do?
Find which columns caused the explosion, usually a few high-cardinality categoricals. Group rare categories into Other, or switch those columns to frequency, target or hashing encoding. Use sparse matrices so zeros take no memory. Tree libraries like LightGBM and CatBoost can handle categoricals natively without one-hot. Then remove near-constant columns and check that validation scores hold up with the smaller feature set.
Tips to crack the Tower Research Capital Data Science interview
Practise probability puzzles, expected value and brain teasers, which are common in quant trading interviews.
For developer roles, revise C++ deeply, including memory management, templates and low-latency coding practices.
Learn the basics of order books, market making and latency so you can discuss how trading systems work.
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; Tower Research Capital interviewers usually ask follow-ups on your first answer.
Frequently asked questions
How many rounds are there in the Tower Research Capital Data Science interview?
Candidates usually go through 5 stages: Online assessment (coding + quant); Technical round 1 (DSA); Technical round 2 (C++ or systems); Quant or probability 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 Tower Research Capital Data Science interview?
This practice set leans on Machine Learning (10), Feature Engineering (5), A/B Testing & Experimentation (4), MLOps and Model Deployment (4). Revise those first, then practise explaining one or two of your own projects end to end, because most Tower Research Capital interviewers ask you to walk through real work.
Are these the exact questions asked at Tower Research Capital?
No. These are curated practice questions that match the skills and difficulty usually tested in fintech interviews like Tower Research Capital's. They are not a leaked or verified list of past questions.
Where does Tower Research Capital hire Data Science professionals in India?
Tower Research Capital has large teams in Gurugram. Openings and locations change often, so check the Tower Research Capital careers page and filter by city and experience.