Have you ever heard someone say, “What is your best guess?” It is certainly no surprise that some assumptions are better than others. Whether they are wrong or good, assumptions give us at least some information as we try to decide on a course of action or choice. Using conjecture as a guide in decision making is not ideal, but it is better than nothing.
On the other hand, if one guess is terrible enough, it might be better not to guess at all! After all, some of us are better at guessing than others.
Companies looking for a data scientist want to have people who can make good guesses, because sometimes the role requires conjecture. Therefore, future data scientists who go through the interview process need to show that they have a solid handle in making an assumption, estimating or, combining these two terms, an assumption.
That is why today we are covering the top questions about assumptions about data science interviews (and candidates for positions in similar, related fields!). If you want to become a data scientist, business analyst, data architect or consultant, you need to know this type of question.
But first, what in the world is conjecture?
What is a guess?
The term “assumption” is a coup d’etat of “assumption” and “evaluation”. Assumptions are estimates based on available limited information. The assumption is based on an information assumption, not an exact answer.
The assumptions have the following five characteristics:
- Meaning: Understanding the problem, understanding its purpose and why you want to solve it
- Definition: The explanation, the object in question, and the input / output of the process flow
- Guessing: thinking and reaching a conclusion
- Evaluation: Make an estimate based on the numbers you need to work with
- Generating an idea: Take the concept and implement it with research and development
Tips for evaluating data science
Although guessing questions do not provide accurate answers, you can still adopt certain habits and tactics that can improve the quality of your answers. Keep these tips in mind:
- Remember, there is no such thing as the right answer: so please don’t bother looking for the right solution; it will not happen.
- Write things down: Write down each part of the question and if the question requires segmentation, create a flowchart showing each segment. The interviewer may want to see your calculation sheet, so do not make the sheet illegible or full of rough calculations.
- Practice rounding: Don’t worry about fractions or decimals – round your numbers to the nearest whole number.
- Facts top feelings. Avoid relying on your inner feelings. Logic and facts (even if you only have a few) carry more weight than how you feel or believe.
- Be calm: You may get a strange question, but don’t let that shake you. Every question has an answer, no matter how strange.
- Take some time and think about things: You don’t get speed points. Pause and think about the question; calm your mind and think things through rationally.
- Clarify your thoughts, then express them: once you have had the opportunity to look at all the angles and use all the facts you have, come up with an answer in your head, and then express it.
- Remember, there is no wrong answer: this concept is important enough to be repeated. There are no correct answers! If you hold the answer until you come up with the perfect answer, you will be dead in the water and the interviewer will not be impressed.
Guess questions and answers
Here is a collection of ten of the most common questions for guessing data science interviews, covering all areas of expertise, from beginners to experienced professionals. Some of the questions may cover already covered concepts, but they are included anyway in order to create a definitive list of guessing questions.
1. What is a guess?
The assumption is an assumption based on existing information; approximate value based on available data.
2. How do you solve a question of conjecture?
You can solve a question with a guess by dividing it into four steps:
First, clarify any vague terms in the application.
Second, break large numbers into smaller, easier-to-use parts.
Third, use basic knowledge to evaluate each piece.
Finally, consolidate all the parts and present your conclusions.
3. Give some examples of guessing questions.
Here are some typical guessing questions:
What is the current number of Android phones used in Delhi?
How many square inches of pizza do Americans consume per day?
How much tea do people in the UK drink each day?
How many golf balls can you fit in a MINI Cooper?
4. What is the function of conjecture questions in Data Science?
First, they help to assess the ability of the data analyst to understand the situation.
Second, they show the scope of the data analyzer’s ability to connect things and arrive at an answer.
Third, they measure how well the analyzer can prioritize or reject various parameters.
Finally, they show how well the analyzer can handle limited data.
5. What are the two methods of approaching guessing questions?
Top-down method. Start with the largest possible universe (of which it is part of the assumption), apply sets of conditions and filters, reducing the numbers of the universe to something that works for evaluation.
Bottom-up method. Start with low-level statistics and build your path to response. For example, if you want to calculate the seller’s monthly income, you need to calculate his weekly income, then multiply the result by 4.
6. Explain the three different assumptions based on the way you approach a decision.
The three types are:
Household approach: This approach deals with assumptions based on households.
Population approach: This approach addresses questions about population assumptions, such as determining how many people live in an area.
The structural approach: This approach creates assumptions for situations such as finding out how many vehicles use a particular bridge each day.
7. How would you determine how many iPhone users exist in the UK?
First, clarify that the issue includes all iPhone models. Second, determine the population. The United Kingdom has approximately 67 million people, about 40 percent of whom are children and the elderly, so I will not count them. This means that we are left with 40,200,000 potential iPhone users.
Since iPhones are usually expensive, we will further eliminate anyone below the middle class. About 25 per cent of the UK population is in the middle class and 6 per cent is in the upper class. This gives us 12,462,000 potential iPhone users. According to current statistics, iPhones have a global market share of 22 percent, giving a final estimated result of 8,844,000.
8. How many socks do you need to remove from a bag that contains blue and red socks to get a pair of matching socks?
Say you reach out and take out a red sock, then a blue one. Since the third attempt will give you another red or blue sock, you will have your pair. So, you need three attempts.
9. How many people live in your apartment building?
Your city has a standardized apartment configuration of 10-storey structures, each floor with 20 apartments. These are 200 apartments.
Four people live in the middle apartment. So at first glance, your estimate will be 800 people. But not so fast! Common wisdom says that 10 percent of the apartments in the building are uninhabitable! This means that you assume that 720 people live in your building.
10. How many cups of coffee do Americans drink in New York per month?
Let’s start by finding that people drink fewer cups of coffee on the weekends because they don’t need to increase caffeine for their work. Then we have to look for the population of New York, which is about 9 million people.
Now let’s say that 20 percent of these people are children, and you don’t want to drink caffeinated children! Thus, the remaining 30 percent drink coffee every day, 20 percent drink coffee from time to time and 10 percent drink tea instead.
We now assume that coffee drinkers can drink three cups of coffee a day, and people who drink coffee from time to time are satisfied with only two cups a week. Here is the breakdown of the formula:
Daily coffee drinkers: 3 x 0.2 x 7 = 4.2
Occasionally drinking coffee: 1 x 0.2 x 1 = 0.2
Tea drinkers: 0
Total: daily + occasionally + drinking tea = 4.4 cups per day
Per month = 4 x 4.4 x 7.2 million = 126,720,000 cups of coffee per month. This is very Java!
Looking forward to becoming a data specialist? Check out the Data Science Bootcamp program and get certified today.
Want to become a data specialist?
Our world is based on data and the need for data scientists is greater than ever. If you want to start a career as a data scientist, Simplilearn can help you get started. The Data Scientist Master’s program, run in collaboration with IBM, enhances your career in Data Science and provides you with the world-class training and skills you need to succeed in this field. The course offers extensive training on the most sought after skills in data science and machine learning, including practical exposure to critical tools and technologies such as Python, R, Tableau and machine learning concepts. You can become an expert in data science by immersing yourself in the nuances of data interpretation, mastering technologies such as machine learning, and mastering powerful programming skills designed to take your career in data science to the next level.
According to glass door, Data professionals in India can earn an average annual salary of Rs 1,000,000. Glassdoor also reports that data specialists in the United States can make an average annual salary of $ 110,000.
So don’t delay! Visit Simplilearn today and start a rewarding, exciting career in Data Science!