Knowledge About Machine Learning Workflow
The most common question asked in an ML interview is: Describe the workflow of a Machine learning project.
Here, you have to describe the different stages required to build a proper ML project from scratch.
Here is a reference answer.
Stage 1: Data gathering
Stage 2: Data pre-processing
Stage 3: Researching the model
Stage 4: Training & testing
Stage 5: Model Evaluation & Deployment
Why Would You Prune Your Tree
In the context of data science or AIML, pruning refers to the process of reducing redundant branches of a decision tree. Decision Trees are prone to overfitting, pruning the tree helps to reduce the size and minimizes the chances of overfitting. Pruning involves turning branches of a decision tree into leaf nodes and removing the leaf nodes from the original branch. It serves as a tool to perform the tradeoff.
What Are The Applications Of Supervised Machine Learning In Modern Businesses
Applications of supervised machine learning include:
Email Spam Detection
Here we train the model using historical data that consists of emails categorized as spam or not spam. This labeled information is fed as input to the model.
By providing images regarding a disease, a model can be trained to detect if a person is suffering from the disease or not.
This refers to the process of using algorithms to mine documents and determine whether theyre positive, neutral, or negative in sentiment.
By training the model to identify suspicious patterns, we can detect instances of possible fraud.
Don’t Miss: What Not To Say In An Exit Interview
List All Types Of Popular Recommendation Systems Name And Explain Two Personalized Recommendation Systems Along With Their Ease Of Implementation
Popularity based recommendation, content-based recommendation, user-based collaborative filter, and item-based recommendation are the popular types of recommendation systems.Personalised Recommendation systems are- Content-based recommendation, user-based collaborative filter, and item-based recommendation. User-based collaborative filter and item-based recommendations are more personalised. Ease to maintain: Similarity matrix can be maintained easily with Item-based recommendation.
How To Prepare For Machine Learning Interview Questions
Changing careers can seem daunting, but it’s the interview process that’s the most nerve-wracking. It’s a normal feeling to have. But with preparation and practice, you can put your best foot forward during your interviews.
To help you prepare, we’ll explore some of the most common machine learning interview questions in the paragraphs below. Along with the questions, we’ll also provide some tips for how to practice and explain what you can expect during your machine learning interview.
Read Also: How To Write An Exit Interview Letter
How Do I Start A Career In Machine Learning
There is no fixed or definitive guide through which you can start your machine learning career. The first step is to understand the basic principles of the subject and learn a few key concepts such as algorithms and data structures, coding capabilities, calculus, linear algebra, statistics. The next step would be to take up a ML course, or read the top books for self-learning. You can also work on projects to get a hands-on experience.
What Is A Random Forest How Does It Work
Random forest is a versatile machine learning method capable of performing both regression and classification tasks.
Like bagging and boosting, random forest works by combining a set of other tree models. Random forest builds a tree from a random sample of the columns in the test data.
Hereâs are the steps how a random forest creates the trees:
- Take a sample size from the training data.
- Begin with a single node.
- Run the following algorithm, from the start node:
- If the number of observations is less than node size then stop.
- Select random variables.
- Find the variable that does the âbestâ job splitting the observations.
- Split the observations into two nodes.
Recommended Reading: What Questions Do They Ask In A Cna Interview
Q6 How Do You Map Nicknames To Real Names
- This problem can be solved in n number of ways. Lets assume that youre given a data set containing 1000s of twitter interactions. You will begin by studying the relationship between two people by carefully analyzing the words used in the tweets.
- This kind of problem statement can be solved by implementing Text Mining using Natural Language Processing techniques, wherein each word in a sentence is broken down and co-relations between various words are found.
- NLP is actively used in understanding customer feedback, performing sentimental analysis on Twitter and Facebook. Thus, one of the ways to solve this problem is through Text Mining and Natural Language Processing techniques.
Q24 What Is Cluster Sampling
- It is a process of randomly selecting intact groups within a defined population, sharing similar characteristics.
- Cluster Sample is a probability sample where each sampling unit is a collection or cluster of elements.
- For example, if youre clustering the total number of managers in a set of companies, in that case, managers will represent elements and companies will represent clusters.
You May Like: How To Watch The Meghan Markle Interview
What Is Bayes Theorem State At Least 1 Use Case With Respect To The Machine Learning Context
Bayes Theorem describes the probability of an event, based on prior knowledge of conditions that might be related to the event. For example, if cancer is related to age, then, using Bayes theorem, a persons age can be used to more accurately assess the probability that they have cancer than can be done without the knowledge of the persons age.Chain rule for Bayesian probability can be used to predict the likelihood of the next word in the sentence.
Listen To The Hints Given By Your Interviewer
Example: Youâre explaining PCA and state that âwe should find the eigenvalues and eigenvectors of the data matrix Xâ. If your interviewer questions you with âare you sure?â or âcan you interpret the eigenvalues of X?â, there is a high chance your answer is imprecise or wrong. You should react by reconsidering and talking through your answer. In this case, the interviewer expects you to introduce the covariance matrix of X and find its eigenvalues/eigenvectors.
Recommended Reading: How To Do An Online Video Interview
How Can You Choose A Classifier Based On A Training Set Data Size
When the training set is small, a model that has a right bias and low variance seems to work better because they are less likely to overfit.
For example, Naive Bayes works best when the training set is large. Models with low bias and high variance tend to perform better as they work fine with complex relationships.
Free Course: Introduction to AI
How Do You Select Important Variables While Working On A Data Set
There are various means to select important variables from a data set that include the following:
- Identify and discard correlated variables before finalizing on important variables
- The variables could be selected based on p values from Linear Regression
- Forward, Backward, and Stepwise selection
- Lasso Regression
- Random Forest and plot variable chart
- Top features can be selected based on information gain for the available set of features.
Don’t Miss: How To Practice For Coding Interviews
Your Dataset Has 50 Variables But 8 Variables Have Missing Values Higher Than 30% How Do You Address This
There are three general approaches you could take:
Additional advanced questions may include:
- You must evaluate a regression model based on R², adjusted R² and tolerance. What are your criteria?
- For k-means or kNN, why do we use Euclidean distance over Manhattan distance?
- Linear regression models are usually evaluated using Adjusted R² or an F value. How would you evaluate a logistic regression model?
- Explain the difference between the normal soft margin SVM and SVM with a linear kernel.
What Is The Main Key Difference Between Supervised And Unsupervised Machine Learning
Supervised learning technique needs labeled data to train the model. For example, to solve a classification problem , you need to have label data to train the model and to classify the data into your labeled groups. Unsupervised learning does not need any labelled dataset. This is the main key difference between supervised learning and unsupervised learning.
Read Also: How To Prepare For An Engineering Interview
Competition In The Ai Job Market
But this also means competition, and thats where proper and extensive preparation comes in. The interview process for AI and deep learning positions is based around progressively more difficult and increasingly specific questions, and in a field as young as ours, those questions can cover an enormous range of topics.
Even when the topic is familiar, the question may not be, you can expect to be asked to:
- Solve unusual and unique problems on the fly
These interviews pose their own set of challenges, above and beyond competence at the job and familiarity with the systems, languages, libraries, equations, and processes that distinguish a deep learning pro.
Examine The Organizations Website
Job scams are plentiful today! If this employer has no website, move on.
Both the employers website and the LinkedIn Company page present the party line about the organization what they tell the world, and potential customers/clients, about themselves. As you read, consider: does the information raise any questions or concerns for you OR do you find opportunities and interesting work?
On the employers website, study the home page, but dont stop there. Read the About Us and Contact Us sections to learn more about who they are and who is in charge. Then, look around at the other pages.
- Know the industry or purpose of the organization. Be sure that is what you expect and want to be involved in.
- Become familiar with the products or services. Know the brand names, if any, or at least the purpose or function.
- Check for press releases or the latest news about the organization.
- Look for names of the senior officers or founders and other highly-visible employees. Are any of them familiar to you or perhaps known to you?
- Where are they located?
- Do they have their jobs posted?
Read How to Leverage the Information on Employer Websites for more details on digging out information from the employers website.
You May Like: How Many Realtors Should You Interview
Check Out What Vault Comparably And Glassdoor Show About The Employer
Vault.com, Comparably.com, and Glassdoor.com collect and make information about many different employers available.
Valut.com collects reviews and other information about employers to make available to job seekers. They also put together lists of different kinds of employers, annually Top Law Firms, Top Consulting Firms, Best Advertising Agencies, and many more.
Comparably.com offers lists of the best-paying jobs, equity compensation by employer, top rated companies by location, and much more about an employers culture rating the management team, treatment of women and minorities, and more.
Glassdoor.com also collects employee reviews. An employers reviews may include a collection of questions that specific employers seem to use in their job interviews.
In both cases, the information is provided by people who visit the website and who may, or may not, be providing good information, current, reliable, and/or well-articulated. So, use the information with that in mind.
Comparably and Glassdoor also have salary information available, reported by employees, to be used cautiously, as described below.
What Do You Understand By Precision And Recall
In pattern recognition, The information retrieval and classification in machine learning are part of precision. It is also called as positive predictive value which is the fraction of relevant instances among the retrieved instances.
Recall is also known as sensitivity and the fraction of the total amount of relevant instances which were actually retrieved.
Both precision and recall are therefore based on an understanding and measure of relevance.
Don’t Miss: How To Set Up A Video Interview
Explain The K Nearest Neighbor Algorithm
K nearest neighbor algorithm is a classification algorithm that works in a way that a new data point is assigned to a neighboring group to which it is most similar.
In K nearest neighbors, K can be an integer greater than 1. So, for every new data point, we want to classify, we compute to which neighboring group it is closest.
Let us classify an object using the following example. Consider there are three clusters:
- Tennis ball
Let the new data point to be classified is a black ball. We use KNN to classify it. Assume K = 5 .
Next, we find the K nearest data points, as shown.
Observe that all five selected points do not belong to the same cluster. There are three tennis balls and one each of basketball and football.
When multiple classes are involved, we prefer the majority. Here the majority is with the tennis ball, so the new data point is assigned to this cluster.
What Are Some Methods Of Reducing Dimensionality
You can reduce dimensionality by combining features with feature engineering, removing collinear features, or using algorithmic dimensionality reduction.
Now that you have gone through these machine learning interview questions, you must have got an idea of your strengths and weaknesses in this domain.
Get an overview of AI concepts, workflows, and performance metrics with the AI and Machine Learning Certification Courses.
Also Check: What To Prepare For A Phone Interview
Why Do You Want To Work For
When a hiring manager asks this question, not only do they want to know why you want to work for them, but they also want to know what you know about the company. This question tests how well you know what the company does and how passionate you are about the work they doso make sure you know the company well and can speak truthfully about your desires to work there.
A Data Set Is Given To You About Utilities Fraud Detection You Have Built Aclassifier Model And Achieved A Performance Score Of 985% Is This A Goodmodel If Yes Justify If Not What Can You Do About It
Data set about utilities fraud detection is not balanced enough i.e. imbalanced. In such a data set, accuracy score cannot be the measure of performance as it may only be predict the majority class label correctly but in this case our point of interest is to predict the minority label. But often minorities are treated as noise and ignored. So, there is a high probability of misclassification of the minority label as compared to the majority label. For evaluating the model performance in case of imbalanced data sets, we should use Sensitivity or Specificity to determine class label wise performance of the classification model. If the minority class labels performance is not so good, we could do the following:
Don’t Miss: What To Ask A Babysitter In An Interview
Who Has Designed These Interview Preparation Tools And Content
Lavanya holds a PhD in Machine Learning and a masters in Computer Graphics. She has worked for over 10 years with companies like Amazon, InMobi and Myntra. In addition, she has also done collaborative projects with ML teams at various companies like Xerox Research, NetApp and IBM. During her career she has interviewed over a 100 candidates. She has also done sevaral mock interviews for job aspirants and is trying to build tools to address common challenges candidates face during job interviews.
When I was trying to get into an ML role, even getting interviews was challenging, since my background was in Industrial Engineering. One session with MachineLearningInterview and I realized what mistakes I was making in my resume that were leading to bad interviews. It took me just 3 more interviews to crack a new job. Now Ive transformed into becoming a Data Scientist. Im definitely going to take their support when I change jobs next time.
In the meantime, here are some interview questions and answers to get started with your ML Interview Preparation! . You have access to more free content by subscribing to our mailing list.
How do you design a system that reads a natural language question and retrieves the closest FAQ answer?
There are multiple approaches for FAQ based question answering
What To Expect In A Machine Learning Interview
Whether it’s all virtual or some portions are in person, there will be a live aspect to your interview. Hiring managers and recruiters like to see how their potential new employees can communicate and perform under a little bit of pressure. It’s also a great chance to see if both manager and employee personalities are a good fit.
All the same standard advice applies to virtual interviews as those that occur in person. Be sure to dress professionally and in line with the company’s dress code. Show up a few minutes early so that you’re ready to go. This will also give you time to sort out any software or connectivity issues.
Before delving into the technical aspects of machine learning, your interviewer may warm up with questions about your experience and passion for the field. These questions may include:
- What role do you think data plays in our business?
- Can you share how you resolved a programming problem recently?
- How do you stay up to date on the latest in the field of machine learning?
- What excites you the most about a career in machine learning?
- Where do you think machine learning is underutilized in our industry?
Let your personality and interests shine through when answering these questions. You may even strike up an interesting conversation with your future boss. Don’t be shy. Show you know what you’re talking about and that you’re happy to be there. Being professional doesn’t mean you need to be emotionless.
Also Check: Should You Email After An Interview