SHOPEE CODE LEAGUE 2021

ADMINISTRATIVE GUIDE V1 FOR PARTICIPANTS

Dates of 6 to 20 March 2021

Competition:

Dates of Training workshops will be held from 19 February to 15 March 2021.

Training
Workshops: For more details, please check our website ​here​ and refer to our weekly
newsletter announcements.

Content: Event Background

Shopee Code League Details
List of Resources
Hear from Us
Further Information
● Annex A - Compulsory Parental Consent Form
● Annex B - Shopee Code League FAQ
● Annex C - Terms and Conditions
● Annex D - Privacy Policy

1
 EVENT BACKGROUND
Shopee Code League is a 3-week coding challenge consisting of 3 coding competitions open to
all students and professionals across the region. The competitions, specially designed by the
Shopee tech teams, cover data analytics, data science and algorithmic problems. Participants
must analyse the datasets, draw insightful conclusions and solve the problems in a specified
amount of time.

Through Shopee Code League, we aim to:

● Equip undergraduates and professionals across the region with essential tech skills and
expertise to prepare them for the new digital economy
● Bring the tech communities closer through problem solving and knowledge sharing
together across the region
● Provide participants with the opportunity to work on real datasets and challenges in the
Internet industry

 SHOPEE CODE LEAGUE DETAILS: HOW IT WORKS

Shopee Code League will operate online entirely from 6 to 20 March 2021.

● Competitions are held every weekend of the league (6 March - Data Analytics
Challenge, 13 March - Data Science Challenge, 20 March - Programming Challenge)
● Participation in all competitions is not compulsory. Your team is free to choose which
competitions to participate in.
○ However, participating in more competitions will allow your team to gather more
points and rise up the leaderboard.

You can look forward to attending online sharings and training workshops organized by Shopee
tech teams and our training partners, on the following topics:

● Programming Languages such as Python

● Data Analytics
● Data Science
● Software Engineering

2 
 LIST OF RESOURCES
We have curated the following non-exhaustive resources that you and your team can look into,
in preparation for Shopee Code League 2021.
I. Online Learning Platforms
II. Understanding Data Science Models
III. Engineering Algorithm Questions

 I. Online Learning Platforms

Section I offers four online learning platforms that may be useful in your preparation for Shopee
Code League. These platforms offer video tutorials, courses and other resources outlining
various data-driven concepts and programming language skills.
Disclaimer: We are not promoting any of these platforms, these are just suggestions you can
look into.

Platforms Overview

Coursera Coursera provides one of the longest-established online data science

educations through John Hopkins University. Learners can access
thousands of courses for free, without access to features like graded
homework assignments or certificates of completion.

● Data Science ​Courses

● Data Science Specialisation ​Course
● C for Everyone: Programming Fundamentals
● Python Programming: A Concise Introduction
● Programming Languages, Part A
● Programming Languages, Part B
● Programming Languages, Part C
● Code Yourself! An Introduction to Programming
● Introduction to Programming with MATLAB
● C++ For C Programmers, Part A
● Computer Vision Basics
● Algorithms, Part I
● Algorithms, Part II
● Analysis of Algorithms
● Computer Science: Algorithms, Theory, and Machines
● Computer Science: Programming with a Purpose

RealPython At Real Python, you’ll learn real-world programming skills from a

community of professional Pythonistas from all around the world. Find
courses and articles according to your level of expertise.

● I’m new to Python and to programming in general

● I’m an intermediate Python developer—How do I take my skills

3 
 and my productivity to the next level?
● I’ve got experience with other programming languages—How
do I get up to speed with Python as quickly as possible?

Udemy Udemy offers highly-rated data science courses that will help you
learn how to visualize and respond to new data, as well as develop
innovative new technologies. The free courses offer online video
content, whereas the paid courses include certificate of completion,
instructor Q&A and instructor direct message.

● Introduction to Python Programming

● Python Core and Advanced
● Python For Data Science
● Java Tutorial for Complete Beginners
● Java Multithreading
● Java Programming Basics
● Practice Java by Building Projects
● Java 8 Functional Programming: Lambda Expressions Quickly
● Learn how to use all Java keywords
● Intermediate Level C++

edX edX is the trusted platform for education and learning. Founded by
Harvard and MIT, edX is home to more than 20 million learners, the
majority of top-ranked universities in the world and industry-leading
companies.

● Data Science ​Courses

● Software Engineering ​Courses
● Java Programming Fundamentals
● CS50's Web Programming with Python and JavaScript
● Visualizing Data with Python
● Deep Learning with Python and PyTorch
● Software Engineering Essentials

Udacity Udacity partners with leading technology companies to learn how

technology is transforming industries, and teach the critical tech skills
that companies are looking for in their workforce.

With their powerful and flexible digital education platform, even the
busiest learners can prepare themselves to take on the most
in-demand tech roles.

● Business Analytics
● Predictive Analytics for Business
● Programming for Data Science with Python

4 
 ● Data Structures and Algorithms

 II. Understanding Data Science Models

Section II offers a series of data science models/topics that would be helpful when solving the
Shopee Code League problem statements. You would find links to articles and other online
resources, categorised by model type.

Image Classification Model

1) InceptionV3
● A Simple Guide to the Versions of the Inception Network
● Review: Inception-v3 — 1st Runner Up (Image Classification) in ILSVRC 2015

2) MobileNet
● Transfer Learning using Mobilenet and Keras
● Review: MobileNetV1 — Depthwise Separable Convolution (Light Weight Model)
● Creating insanely fast image classifiers with MobileNet in TensorFlow

3) SqueezeNEt
● Review: SqueezeNet (Image Classification)

4) VGGNet
● What is the VGG neural network?
● Review: VGGNet — 1st Runner-Up (Image Classification), Winner (Localization)
in ILSVRC 2014
● Difference between AlexNet, VGGNet, ResNet, and Inception

5) ResNet
○ Introduction to ResNets
○ An Overview of ResNet and its Variants
Intuition For: ResNet — Deep Residual Learning for Image Recognition

6) ResNeXt
● Understanding and Implementing Architectures of ResNet and ResNeXt for
state-of-the-art Image Classification: From Microsoft to Facebook [Part 1]
● Understanding and Implementing Architectures of ResNet and ResNeXt for
state-of-the-art Image Classification: From Microsoft to Facebook [Part 2]
● Review: ResNeXt — 1st Runner Up in ILSVRC 2016 (Image Classification)
● Enhancing ResNet to ResNeXt for image classification

5 
Image Segmentation Model
1) SegNet
● Summary of — SegNet: A Deep Convolutional Encoder-Decoder Architecture for
Image Segmentation
● Review: SegNet (Semantic Segmentation)
● Understanding of Semantic Segmentation & How Segnet Model work to perform
Semantic Segmentation

2) Deeplab
● The Evolution of Deeplab for Semantic Segmentation
● Semantic Image Segmentation with DeepLab in TensorFlow
● How to use DeepLab in TensorFlow for object segmentation using Deep
Learning

3) MaskRCNN
● Simple Understanding of Mask RCNN
● Computer Vision: Instance Segmentation with Mask R-CNN
● Mask R-CNN for Ship Detection & Segmentation

Text Model
1) RNN
2) LSTM
● Understanding RNN and LSTM
● Recurrent Neural Networks and LSTM explained
● Recurrent Neural Networks
● Report on Text Classification using CNN, RNN & HAN
● Generating text using a Recurrent Neural Network
● Multi-Class Text Classification with LSTM
● Illustrated Guide to LSTM’s and GRU’s: A step by step explanation
● The magic of LSTM neural networks
● Video/Course​: Long Short Term Memory (LSTM)

Image Processing

● Getting Started with Image Processing using Python

● Exploring Image Processing Techniques — OpenCV
● Image processing with Python & Open-CV part-1
● Image processing using Python & Open-CV part-2
● Image processing using Python & Open-CV part-3
● Image Processing using Python basic -I

6 
Convolution Neutral Network
● Understanding of Convolutional Neural Network (CNN) — Deep Learning
● A Beginner Intro to Convolutional Neural Networks
● A Brief Guide to Convolutional Neural Network(CNN)
● Convolutional Neural Networks — CNN
● The best explanation of Convolutional Neural Networks on the Internet!

Object Detection
● Understanding Object Detection
● Object Detection with 10 lines of code
● Beginner’s Guide to Object Detection Algorithms

Natural Language Processing

● Natural Language Processing is Fun!
● A Practitioner's Guide to Natural Language Processing (Part I) — Processing &
Understanding Text

TF-IDF
● TF-IDF from scratch in python on real world dataset.
● What is TF-IDF in Feature Engineering?
● TF IDF | TFIDF Python Example
● How to process textual data using TF-IDF in Python
● TF-IDF/Term Frequency Technique: Easiest explanation for Text classification in NLP
using Python (Chatbot training on words)

Word Embeddings
● Introduction to Word Embedding and Word2Vec
● Word embeddings in NLP
● Video​: Using Word Embeddings

BERT - Language Modeling

● BERT Explained: State of the art language model for NLP
● Understanding BERT: Is it a Game Changer in NLP?
● Google BERT — Pre Training and Fine Tuning for NLP Tasks
● Building State-of-the-Art Language Models with BERT
● Google Scholar Papers/Articles​ on BERT

Classification Models
● Machine Learning Classifiers
● A Lesson on Modern Classification Models
● Classification Algorithms Used in Data Science

7 
 ● Intro to types of classification algorithms in Machine Learning (2017)

​Transformer
● What is a Transformer?
● How Transformers Work
● Transformer: A Novel Neural Network Architecture for Language Understanding​ (2017)

Sequence to Sequence Model

● Understanding Encoder-Decoder Sequence to Sequence Model​ (2019)
● Sequence To Sequence Models (2018)
● Sequence to sequence model: Introduction and concepts (2017)
● NLP | Sequence to Sequence Networks| Part 1| Processing text data
● NLP | Sequence to Sequence Networks| Part 2| Seq2seq Model (EncoderDecoder
Model)
● Sequence Modeling with Deep Learning

Attention Model
● Brief Introduction to Attention Models
● An introduction to Attention
● Intuitive Understanding of Attention Mechanism in Deep Learning
● Attention and its Different Forms
● Attention Mechanisms in Deep Learning — Not So Special
● Coursera ​Video​: Attention Model

 III. Engineering Algorithm Questions

Section III offers tips and tricks on answering algorithm questions.

● Software Engineering Must Know: Algorithms

● Top Algorithms and Data Structures You Really Need To Know
● 8 Common Data Structures every Programmer must know
● Data Structures
● Fundamentals of Algorithms

8 
 PAST PROBLEM STATEMENTS

Data Analytics Problem Statements

Participants are required to come up with a script which can output the correct answer.
● Order Brushing

● Logistics

● Marketing Analytics

Data Science Problem Statements

Participants will have to build a model which can accurately predict the labels for each of the
rows in the given datasets.
● Product Detection

● Title Translation

● Sentiment Analysis

Programming Contest Questions

Participants will need to come up with the correct solutions to each of the test cases provided by

the Shopee Engineering teams.

● Shopee Programming Contest #1

● Shopee Programming Contest #2

9 
 HEAR FROM US
The Shopee Team will keep you updated via email throughout the entire Shopee Code League.
Do keep a look out for emailers and ensure your email account will accept emails from
techsg@shopee.com​.

You will be receiving an Administrative Guide V2 that encloses more details for your information
and action (e.g. competition platform registrations) and Calendar of Events a week prior to the
first competition​.

Should you have any further questions, please look into our ​Annex B ​- Shopee Code League
FAQ. If you are unable to find your questions and answers in our FAQ, please send your
enquiries to ​techsg@shopee.com​ and we will get back to you in 5 working days.

 FURTHER INFORMATION
The following Annexes are enclosed for your information.
● Annex A - ​Compulsory Parental Consent Form
● Annex B - ​Shopee Code League FAQs
● Annex C - ​Terms and Conditions
● Annex D - ​Privacy Policy

10 
 ANNEX A

 
COMPULSORY PARENTAL CONSENT FORM

If you are under the age 18, please access the parental consent form ​here​.

This parental consent form is compulsory in order to guarantee your participation in Shopee
Code League. E-signature and contact details from parents/guardians are required.

You should receive a confirmation email upon successful submission.

ANNEX B

 
SHOPEE CODE LEAGUE FAQs

You would be able to find answers to Frequently Asked Questions (FAQs) regarding Eligibility,
the Competition and Registration ​here​.

ANNEX C
 
TERMS AND CONDITIONS

Shopee reserves the right to disqualify any Participants and/or teams at its sole discretion if
such Participants and/or teams, where applicable is/are in breach of these Competition ​Terms
and Conditions​ of Shopee Code League 2021.

ANNEX D
 
PRIVACY POLICY

By consenting and submitting the registration form, you have acknowledged and agreed that
you accept the practices, requirements, and/or policies outlined in our Competition Privacy
Policy of Shopee Code League 2021 ​here​.

11