Prepare for and practice interview questions from Tokopedia across topics like Machine Learning, Algorithms, Analytics and more.

Tokopedia Interview Questions

Tokopedia Interview Guides

A/B Testing

How would you determine if the new model predicts delivery times better than the old model

Delivery Estimate Model

How would you analyze the effectiveness of this new feature?

Green Dot

How would you design a two-week A/B test to determine whether a pricing increase is a good business decision

Testing Price Increase

How would you determine which search engine performed better and which metrics would you track

Comparing Search Engines

How should we test it, measure success of the test, and eventually roll it out

Building Lyft Line

Machine Learning

In which case would you use a bagging algorithm versus a boosting algorithm

Bagging vs Boosting

What kind of model would we build and what features would we use

Food Prep Features

How would you justify the complexity of building such a model and explain the predictions to non-technical stakeholders

Justify a Neural Network

How would you improve a classification model with low precision

Low Precision

Minimize Wrong Orders

Product Sense & Metrics

How would you measure the success of the Instagram TV product

Instagram TV Success

Google Maps Improvement

Unified Inbox

Let's say that we want to improve the "search" feature on the Facebook app.

Improve Search Results

What are the top five metrics you would start tracking to understand the health of Google Docs

Docs Metrics

Business Case

What methods could you use to increase recall?

Search Algorithm Recall

How would you decide whether Google should build a game feature for Google Home

Game Feature Home

Diagnose why the pricing algorithm is under-pricing a consumer product

Underpricing Algorithm

How would you approach promoting Meta's products in an emerging market

Meta in an Emerging Market

Statistics

What are the assumptions of linear regression?

Assumptions of Linear Regression

How do you detect and handle correlation between variables in linear regression, and what happens if you ignore it

Correlation in Regression

How would you tackle multicollinearity in multiple linear regression

Multicollinearity in Regression

Let’s say we’re comparing two machine learning algorithms. In which case would you use a bagging algorithm versus a boosting algorithm? 

Give an example of the tradeoffs between the two.

In machine learning, when would you use a bagging algorithm over a boosting algorithm?

In machine learning, when would you use a bagging algorithm over a boosting algorithm?

Bagging vs. Boosting

Let’s say you’re a Product Data Scientist at Instagram. How would you measure the success of the Instagram TV product?

What is the primary goal of Instagram TV as a product feature?

What is the primary goal of Instagram TV as a product feature?

Let’s say we want to build a new delivery time estimate model for consumers ordering food delivery.

How would you determine if the new model predicts delivery times better than the old model?

When rolling out a new delivery time estimate model in production, what is an important consideration?

When rolling out a new delivery time estimate model in production, what is an important consideration?

Delivery Estimate Model I

What is one way to measure the performance of a new delivery time estimate model for food delivery?

What is one way to measure the performance of a new delivery time estimate model for food delivery?

Delivery Estimate Model II

Let’s say that you’re the PM on Google Maps.

<ol>
<li>How would you improve Google Maps?</li>

<li>What metrics would you check to see if your feature improvements are successful?</li>
</ol>

What are the assumptions of linear regression?

Which assumption of the residuals of the standard linear regression model can not be overcome by increasing the sample size?

Regression assumptions

Let’s say that you work at a B2B SAAS company that’s interested in testing the pricing of different levels of subscriptions.

Your project manager comes to you and asks you to run a two-week-long A/B test to test an increase in pricing.

How would you approach designing this test? How would you determine whether the increase in pricing is a good business decision?

Let’s say you’re working on a building a better search engine for Google. You build it and want to see if it serves better results than the existing one in production.

How would you determine which search engine performed better? Which metrics would you track?

Let’s say you work as a data scientist at Amazon. You want to improve the search results for product search but cannot change the underlying logic in the search algorithm.

What methods could you use to increase recall?

How would you tackle multicollinearity in multiple linear regression?

Let’s say we’re working on a new feature for LinkedIn chat. We want to implement a green dot to show an “active user” but given engineering constraints, we can’t AB test it before release.

How would you analyze the effectiveness of this new feature?

Let’s say you work for an e-commerce company. Vendors can send products to the company’s warehouse to be listed on the website. Users are able to order any in-stock products and submit returns for refunds if they’re not satisfied.

The front end of the website includes a vendor portal that provides sales data in daily, weekly, monthly, quarterly, and yearly intervals.

The company wants to expand worldwide. They put you in charge of designing its end-to-end architecture, so you need to know what significant factors you’ll need to consider. What clarifying questions would you ask?

What kind of end-to-end architecture would you design for this company (both for ETL and reporting)?

How would you design a data warehouse for a e-commerce company looking to expand internationally?

International e-Commerce Warehouse

To improve customer experience on Uber Eats, what key parameters would you focus on improving?

Delivering an exceptional customer experience by focusing on key customer-centric parameters

Uber Eats Customer Experience

How would you decide whether or not to create a product, like a job board, for Facebook?

Imagine Facebook is creating a job board. How would you design an A/B test to evaluate its effectiveness?

Assessing the market potential and then use A/B testing to measure its effectiveness against user behavior

Facebook Job Board Design

Let’s say that we want to improve the “search” feature on the Facebook app.

We want to specifically improve search results for people looking for things to do in San Francisco.

What would you investigate and what metrics would you come up with to understand if the current functionality in the search was performing well?

You’re a data scientist for Instagram’s product team.

A product manager proposes changing the platform’s messaging system to allow interactions with other platforms and third-party businesses.

For example, Instagram could partner with GrubHub to allow the company to send messages to Instagram users about their GrubHub order.

Question: How would you determine whether this change is a good idea?

Let’s say you work as a data scientist at DoorDash. 

You are tasked to build a machine learning system that minimizes missing or wrong orders placed on the app.

How would you go about designing this system?

Let’s say that you work at Facebook. Your team focuses on helping small businesses increase sales through the Marketplace app on Facebook.

How would you determine the customer service quality through the chat box for all interactions involving small businesses selling items to consumers?

How would you determine customer service quality through a chat box?

Measuring Customer Service Quality

Analytics

When an interviewer asks a question along the lines of:

<ul>
<li>What would your current manager say about you? What constructive criticisms might he give?</li>
<li>What are your three biggest strengths and weaknesses you have identified in yourself?</li>
</ul>

How would you respond?

When asked about your strengths in an interview, what is an effective way to respond?

When asked about your strengths in an interview, what is an effective way to respond?

Your Strengths and Weaknesses I

Which of the following is an acceptable strategy when discussing weaknesses in an interview?

Which of the following is an acceptable strategy when discussing weaknesses in an interview?

Your Strengths and Weaknesses II

What do you tell an interviewer when they ask you what your strengths and weaknesses are?

Your Strengths and Weaknesses

Behavioral

Let’s say you’re a data scientist working on pricing different products on our ecommerce site. The online price is dependent on the availability of the product, the demand, and the logistics cost of providing it to the end consumer. 

You discover our algorithm is vastly under-pricing a certain consumer product. What are the steps you take in diagnosing the problem?

Let’s say your manager asks you to build a model with a neural network to solve a business problem.

How would you justify the complexity of building such a model and explain the predictions to non-technical stakeholders?

Which is the following domains is generally NOT a good use case for using a deep neural net?

Which is the following domains is generally NOT a good use case for using a deep neural net?

Neural Net Use Cases

Let’s say that you’re trying to run some data processing and cleaning on a <code>.csv</code> file that’s currently 100GB large.

You realize it’s too big to store in memory, so you can’t clean the file using <code>pandas.read_csv()</code>. How would you get around this issue and clean the data?

How would you clean a 100GB .csv file without loading it into memory

Processing Large CSV

Data Pipelines

Let’s say you are working on Google Docs. A product manager comes to you and asks how the product is doing. 

What are the top five metrics that you would start tracking to understand the health of Google Docs?

An ecommerce company is experiencing a reduction in revenue for the past 12 months. You have the following transaction data:

<ul>
<li>Date of sale</li>

<li>Total $ Amount paid by customer</li>

<li>Profit Margin per unit</li>

<li>Quantity of item</li>

<li>Item category</li>

<li>Item subcategory</li>

<li>Marketing attribution source</li>

<li>% discount applied</li>
</ul>

How would you analyze the dataset to understand exactly where the revenue loss is occurring?

How would you analyze the dataset to understand exactly where the revenue loss is occurring?

Evaluating Revenue Decline

Let’s say we want to build a model to predict the time spent for a restaurant to prepare food from the moment an order comes in until the order is ready. 

What kind of model would we build and what features would we use?

Let’s say you’re working on DoorDash demand side deliveries. DoorDash is launching delivery services in New York City and Charlotte and needs a process for selecting dashers (delivery drivers).

Let’s say we want to create a model to determine which Dashers should deliver a particular order.

We currently have these features already in our model.

<ul>
<li>Dasher distance to the restaurant</li>
<li>Number of Dasher reviews from customers</li>
<li>Number of Dasher successful deliveries</li>
</ul>

Which feature would be the best additional input to our existing features to improve the model?

Let's say you're working on DoorDash demand side deliveries. DoorDash is launching delivery services in New York City and Charlotte and needs a process for selecting dashers (delivery drivers).

Let's say we want to create a model to determine which Dashers should deliver a particular order.

We currently have these features already in our model. 

- Dasher distance to the restaurant
- Number of Dasher reviews from customers
- Number of Dasher successful deliveries

Which feature would be the best additional input to our existing features to improve the model?



Dasher Model

Let’s say you’re tasked with building a classification model to determine whether a customer will buy on an e-commerce platform after making a search on the homepage.

You find that your model is suffering from low precision.

How would you improve it?

How do you detect and handle correlation between variables in linear regression? What will happen if you ignore the correlation in the regression model?

Assume you are receiving CSV files intermittently utilizing an SFTP. Design a pipeline to make this data usable.

SFTP Pipeline

Let’s say that you’re working on building a model to detect potential bombs at a border crossing.

How would you design the model’s inputs and outputs, measure its accuracy, and test your model?

Let’s say you are building a neutral net to detect if a nuclear missile is incoming.

What metric would be most important to look at?

Let's say you are building a neutral net to detect if a nuclear missile is incoming.

What metric would be most important to look at?

Nuclear Missile Detection

How would you design the model's inputs and outputs, measure its accuracy, and test your model

Bomb Detection

Let’s you’re tasked with pitching a new feature for Google Home. Your co-worker comes to you with an idea to build a game feature for Google Home.

How would you go about deciding whether Google should build it?

Let’s say we want to build a new algorithm for Lyft Line.

How should we test it, measure success of the test, and eventually roll it out?

Calculate Moving Average	SQL	Easy
Predict Customer Churn	Machine Learning	Medium
A/B Test Significance	Statistics	Medium
Optimize Query Performance	SQL	Hard
Feature Importance Analysis	Machine Learning	Medium
Clean Missing Data	Python	Easy
Neural Network Architecture	Deep Learning	Hard
Calculate Cohort Retention	SQL	Medium
Bayesian Probability	Statistics	Easy
Recommend Similar Products	Machine Learning	Hard

Tokopedia Interview Questions

Tokopedia Interview Guides

Tokopedia Interview Questions

Challenge

Tokopedia Salaries by Position

Discussion & Interview Experiences

Discussion & Interview Experiences