高频题（0）
1. Marketing
| marketing promotion measure/experiments 0.75hr
ramping a new feature to help merchants grow called 'marketing program' .This feature
will allow merchants to set promotions (like free delivery, discount) at certain period of
time.Like ‘happy hour'
1.any questions？any limitations on participants？ who is paying for the discount benefit？ - no limitation
- merchants are paying cost themselves
2.how to understand if merchants are interests in this?
3.How to define ROI return on investment for merchants
4.What negative impact can you think of with the feature
5. how to you quantify the customer side returns.
6. How to do A/B test for this - select metrics; what to split, why, why not consider a,b,c;
Why t-test
7. Once we’ve done the experiment, how to translate that to side wide impact for ramp
up decisions - asked in details why l made some assumptions and how l project it, why l
can hold true.Start from small markets, monitor, improve.可以在同类型的市场ship这个
experience，然后1）选择不同类型的市场reiterate，或2）继续explore有没有更好的radius
(15 miles, etc.)
ramping a new feature to help merchants grow called 'marketing program' .This feature
will allow merchants to set promotions (like free delivery, discount) at certain period of
time.Like ‘happy hour'
1.any questions？any limitations on participants？ who is paying for the discount benefit？ - no limitation
- merchants are paying cost themselves
2.how to understand if merchants are interests in this?
3.How to define ROI return on investment for merchants
4.What negative impact can you think of with the feature
5. how to you quantify the customer side returns.
6. How to do A/B test for this - select metrics; what to split, why, why not consider a,b,c;
Why t-test
7. Once we’ve done the experiment, how to translate that to side wide impact for ramp
up decisions - asked in details why l made some assumptions and how l project it, why l
can hold true.Start from small markets, monitor, improve.可以在同类型的市场ship这个
experience，然后1）选择不同类型的市场reiterate，或2）继续explore有没有更好的radius
(15 miles, etc.)
2. Predict delivery time
| Before a consumer places an order on DoorDash, we show the expected delivery time. It
is very important for DoorDash to get this right, as it has a big impact on consumer experience. Order lateness /underprediction of delivery time is of particular concern as past experiments suggest that underestimating delivery time is roughly twice as costly as overestimating it .Orders that are very early / late are also much worse than those that are only slightly early / late. In this exercise ,you will build a model to exercise, you will build a model to predict the estimated time taken for a delivery.
Concretely. for a given delivery you must predict the total delivery duration seconds, i.e.,the time from
Start: the time consumer submits the order (created at) TO
End: when the order will be delivered to the consumer (actual_delivery_time)
To help with this,we have provided
Historical¬_data.csv: table of historical deliveries (your training set)
Data_to_predict.csv: data for deliveries that you must predict (label-free test set we will
use for evaluation)
Data_description.txt: description of all columns in historical_data.csv and details of
Data_to_ predict.csv
is very important for DoorDash to get this right, as it has a big impact on consumer experience. Order lateness /underprediction of delivery time is of particular concern as past experiments suggest that underestimating delivery time is roughly twice as costly as overestimating it .Orders that are very early / late are also much worse than those that are only slightly early / late. In this exercise ,you will build a model to exercise, you will build a model to predict the estimated time taken for a delivery.
Concretely. for a given delivery you must predict the total delivery duration seconds, i.e.,the time from
Start: the time consumer submits the order (created at) TO
End: when the order will be delivered to the consumer (actual_delivery_time)
To help with this,we have provided
Historical¬_data.csv: table of historical deliveries (your training set)
Data_to_predict.csv: data for deliveries that you must predict (label-free test set we will
use for evaluation)
Data_description.txt: description of all columns in historical_data.csv and details of
Data_to_ predict.csv
3. Expected Reward from Rolling a Fair Six-Faced Dice
If you roll a fair six-faced dice, where each roll gives you a reward equal to the number on the face, what is the expected reward? If you are allowed to roll again, would the expectation change?
4. Reverse an Integer
How would you reverse an integer, for example, converting 12345 to 54321? What edge cases would you need to consider?
5. Hypothetical Fraud Detection Model Features
If you were to build a fraud detection model, what features would you use?
