Project 2: Prediction Challenge

DAPI Project 2: Predictions for Highway Operations

Explore

DAPI Project 2: Predictions for Highway Operations

DAPI Analytics Project

J.C. Bonilla

Motivation

You are part of an analytics team that is trying to inform amenities design for an interstate highway by evaluation drivers’ preferences. In other words, what type of amenities should be build along the highway.

The data comes from an experiment where a promotional coupon is offered to a driver. The promotion is based on a type of amenity such as Bar, Carry out & Take away, Coffee House, or Restaurant. If the driver accepts the promotion it can be inferred that their preference is toward the same type of amenity service along the highway.

With the coupon a survey is also conducted. The survey describes different driving scenarios including the destination, current time, weather, passenger, etc., and then ask the driver whether he/she will accept the promotion.

Challenge

Run a predictive model to assess the likelihood of a driver accepting the promotional coupon. Then, interpret which amenities are more important for your positively predicted class.

In addition, using the team submission file, score 2684 drivers as with a 1 if the accept the coupon and 0 if they do not. This file will be evaluated using accuracy and f-score

Teams

Team

Name

One

Ali,Raveed

Bhosale,Parth

Modi,Devansh

Zhao,Shanshan

Zhu,Yu

Two

Arumugam,Sricharan

Bodapati,sasank

Patnam,Akhil

Zhang,Zicheng

Zhao,Wei

Three

Chauhan,Gargi

Chen,Lu Yu

Cordero,Jose Miguel

Dhanrajani,Gopal

Singh,Trishita

Four

Chen,Qing

qc869@nyu.edu

El Boulli Rguibi,Yosra

Gandhi,Rushil

Gohil,Mehul Suket

Talwande,Purva

Five

Gowda,Hithesh

Li,Jiayi

Lin,Yuqing

Manoharan,Siddharth

Tian,Yuting

Six

Mathialagan,Poorna Kumar

Mehta,Yashita

Woo,Elizabeth

Wu,Xinyu

Xu,Liying

⁠

Submission Requirements

This project is competition style, asking teams to build a predictive model, tune it, and score a set of 2685 records. In addition, teams need interpret and provide operations analytics recommendations which should emerge from the data and the results of a predictive modeling.

At the end, teams should complete the following:

Presentation: summary of the business problem, work completed, results, and recommendations

Analytics case: what business problem are you solving (be creative)

Model: a tuned model with performance metrics and results

Scores: predictions actions on a set of new users. Visualize results as a histogram

Grading

Presentation: 20%

Model performance and technical approach: 50%

Recommendations: 30%

Deliverables

Presentation:10min

Business problem

Data review & feature engineering

Review of models (please use a table to summarize attempts)

Selected model and feature of importance

Scores distributions

Implications and recommendations

Slides

R code

team#_submission.csv (TIP: Don’t change the layout of the submission file, only add your predictions)

Datasets

⁠

Data for model training⁠

⁠

https://drive.google.com/file/d/127K7mX2zsxZ1sxdLsJPkj4yNXs4RhqBp/view⁠

⁠

Data for scoring and submission available by

4/1/2022

⁠

id: unique number giving to the driver doing the survey

destination: No Urgent Place, Home, Work

passanger: Alone, Friend(s), Kid(s), Partner (who are the passengers in the car)

weather: Sunny, Rainy, Snowy

temperature:55, 80, 30

time: 2PM, 10AM, 6PM, 7AM, 10PM

coupon: Restaurant(<$20), Coffee House, Carry out & Take away, Bar, Restaurant($20-$50)

expiration: 1d, 2h (the coupon expires in 1 day or in 2 hours)

gender: Female, Male

age: 21, 46, 26, 31, 41, 50plus, 36, below21

maritalStatus: Unmarried partner, Single, Married partner, Divorced, Widowed

has_Children:1, 0

education: Some college - no degree, Bachelors degree, Associates degree, High School Graduate, Graduate degree (Masters or Doctorate), Some High School

occupation: Unemployed, Architecture & Engineering, Student, Education&Training&Library, Healthcare Support,Healthcare Practitioners & Technical, Sales & Related, Management, Arts Design Entertainment Sports & Media, Computer & Mathematical, Life Physical Social Science, Personal Care & Service, Community & Social Services, Office & Administrative Support, Construction & Extraction, Legal, Retired,Installation Maintenance & Repair, Transportation & Material Moving,Business & Financial, Protective Service,Food Preparation & Serving Related, Production Occupations,Building & Grounds Cleaning & Maintenance, Farming Fishing & Forestry

income: $37500 - $49999, $62500 - $74999, $12500 - $24999, $75000 - $87499,

$50000 - $62499, $25000 - $37499, $100000 or More, $87500 - $99999, Less than $12500

Bar: never, less1, 1~3, gt8, nan4~8 (feature meaning: how many times do you go to a bar every month?)

CoffeeHouse: never, less1, 4~8, 1~3, gt8, nan (feature meaning: how many times do you go to a coffeehouse every month?)

CarryAway:n4~8, 1~3, gt8, less1, never (feature meaning: how many times do you get take-away food every month?)

RestaurantLessThan20: 4~8, 1~3, less1, gt8, never (feature meaning: how many times do you go to a restaurant with an average expense per person of less than $20 every month?)

Restaurant20To50: 1~3, less1, never, gt8, 4~8, nan (feature meaning: how many times do you go to a restaurant with average expense per person of $20 - $50 every month?)

toCoupon_GEQ15min:0,1 (feature meaning: driving distance to the restaurant/bar for using the coupon is greater than 15 minutes)

toCoupon_GEQ25min:0, 1 (feature meaning: driving distance to the restaurant/bar for using the coupon is greater than 25 minutes)

direction_same:0, 1 (feature meaning: whether the restaurant/bar is in the same direction as your current destination)

direction_opp:1, 0 (feature meaning: whether the restaurant/bar is in the same direction as your current destination)

Y: 1, 0 (whether the coupon is accepted)

Tips

When building recommendation for predictive models, you MUST consider feature of importance in your model

⁠

Motivation

Challenge

Teams

Submission Requirements

Grading

Deliverables

Datasets

Data for model training

Data for scoring and submission available by

Tips

Want to print your doc?
This is not the way.

Try clicking the ⋯ next to your doc name or using a keyboard shortcut (

CtrlP

) instead.