This assignment will allow you to apply your skills in business analytics on real-world data from the field of e-commerce

INSTRUCTIONS TO CANDIDATES

ANSWER ALL QUESTIONS

This assignment will allow you to apply your skills in business analytics on real-world data from the field of e-commerce and customer targeting and practice the scientific methods for rigorous testing and documentation. Passing the assignment is required to participate in the exam for the class Business Analytics and Data Science.
Do not use the "Kernels" feature to make your code public. You must not share large code chunks or complete scripts with other participants! You are required to solve the assignment individually, but we encourage discussing issues and code pieces and sharing insights both offline and on the Kaggle forum.

For the assignment, you are highly encouraged to go beyond the standard methods taught in class, make use of the scientific literature and conduct and document your own experiments with the data. Make sure to consider all stages of a typical modeling process:

· research the relevant technical and task-related knowledge in the literature

· gather, clean and preprocess the relevant data

· select the best model and model parameters

·deploy and assess the model in terms of performance and plausibility
with possibly revision of any step or the whole process.

Setting

Customers send back a substantial part of the products that they purchase online. Return shipping is expensive for online platforms and return orders are said to reach 50% for certain industries and products. Nevertheless, free or inexpensive return shipping has become a customer expectation and de-facto standard in the fierce online competition on clothing, but shops have indirect ways to influence customer purchase behavior. For purchases where return seems likely, a shop could, for example, restrict payment options or display additional marketing communication.

For this assignment, you are provided with real-world data by an online retailer. Your task is to identify the items that are likely to be returned. When a customer is about to purchase a item, which is likely to be returned, the shops is planning to show a warning message. Your task is to build a targeting model to balance potential sales and return risk in order to optimize shop revenue. The data you receive is artificially balanced (1:1 ratio between returns and non-returns).

 Evaluation

The evaluation metric for this competition is the Area-under-the-ROC-curve (AUC) based on the probability scores of your model. The model will be evaluated on the class dataset. To pass the assignment and qualify for the exam, a final AUC score of at least 0.68 on the public leaderboard is required. You can submit multiple predictions and improve your score until the end date of the competition.

For every order-item combination in the dataset, submission files should contain two and only two named columns: orderitemid and return. A higher probability score denotes a higher chance of return (1).
You can open .csv files in a text editor (not Excel) to check that everything is exactly right.

The file should contain a header and have the following format:

user_item_id,return
100001,0.4
100002,0.05
etc. 

Data Description

The data contains real orders by customers of a clothing store. It contains 14 columns that describe the order and customer. The column names should be self-explanatory. In compliance with the shop's wishes, we are unable to answer any further questions regarding the data.
If you detect any issues with the data, please contact Johannes Haupt.

File descriptions BADS_WS_1920_known.csv - The training data for which the returns are known

BADS_WS_1920_unknown.csv - The final test data for which predictions are required
example.R - A brief example script outlining the workflow

Data fields
order_item_id - The elements for which a prediction is required
return - The target column: If a customer has returned the item (1) or kept it (0)
+ columns describing the order

Attachments:

Related Questions

. The fundamental operations of create, read, update, and delete (CRUD) in either Python or Java

CS 340 Milestone One Guidelines and Rubric  Overview: For this assignment, you will implement the fundamental operations of create, read, update,

. Develop a program to emulate a purchase transaction at a retail store. This  program will have two classes, a LineItem class and a Transaction class

Retail Transaction Programming Project  Project Requirements:  Develop a program to emulate a purchase transaction at a retail store. This

. The following program contains five errors. Identify the errors and fix them

7COM1028   Secure Systems Programming   Referral Coursework: Secure

. Accepts the following from a user: Item Name Item Quantity Item Price Allows the user to create a file to store the sales receipt contents

Create a GUI program that:Accepts the following from a user:Item NameItem QuantityItem PriceAllows the user to create a file to store the sales receip

. The final project will encompass developing a web service using a software stack and implementing an industry-standard interface. Regardless of whether you choose to pursue application development goals as a pure developer or as a software engineer

CS 340 Final Project Guidelines and Rubric  Overview The final project will encompass developing a web service using a software stack and impleme