Payment Risk And Payment Fraud: Data Science And Analytics
Published 9/2023
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz
Language: English | Size: 5.94 GB | Duration: 8h 43m
Published 9/2023
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz
Language: English | Size: 5.94 GB | Duration: 8h 43m
we will learn modeling and coding (SQL/Python) knowledge for data science and data analytics in payment risk
What you'll learn
Understand how payment works in general
Understand how fraudsters work, the different payment fraud types and corresponding risky signals
Understand the statistic and ML basics
Understand the SQL basics
Understand the Python basics
Complete one case study to build a decision tree model with Python to solve fraud problem
Complete one case study to
Requirements
No experiences needed, we will learn everything from this course
Description
Hi, this is Kangxiao, I have many years of working experience with industry leaders like Paypal, Google, and Chime. Throughout my entire career, I have used data to do analysis, build models, and solve key business problems.When I learn online, I often run into two issues:The course offers in-depth knowledge, but it doesn't have very broad coverage. In reality, we don't need to be experts for everything. But it will give us a huge advantage if we know the basics for a lot of things.The course focuses too much on the technical side. I find a lot of the courses focus entirely on either coding like how to write Python codes, or stats like the math behind different kinds of ML models. And there are very few courses that link payment risk/fraud, modeling, and coding together to solve real-world problems.In the payment and payment risk industry, people have come to the conclusion that we have to rely on data-driven solutions to fight against the bad actors. This makes data science and data analytics super important for payment risk and payment fraud. Thus, In this course, I want to share my knowledge of data science and analytics in payment risk by offering very broad coverage of payment and payment risk basics, data science, statistics, modeling, and coding, and using case studies to connect data, coding, and stats together. That’s exactly what we do in the real world, in our day-to-day work. The best talents I observe in Paypal, Google, and Chime are the ones who are really good at connecting these dots together to solve complicated problems.I hope this course can help set you ready for your future success in payment and payment risk. Please join us, If any of these interests you. Let's enjoy this journey together!
Overview
Section 1: Introduction
Lecture 1 Introduction
Lecture 2 Course Outline
Section 2: Payment
Lecture 3 Payment Overview
Lecture 4 Card Transactions
Lecture 5 ACH Transactions
Lecture 6 Chargeback and Refund
Section 3: Payment Risk
Lecture 7 Payment Risk Overview
Lecture 8 ATO Introduction
Lecture 9 How to identify ATO
Lecture 10 Stolen Financial and NSF overview
Lecture 11 How to identify SF and NSF
Lecture 12 Family Fraud Overview
Lecture 13 How to identify Family Fraud
Lecture 14 Merchant Risk Introduction
Lecture 15 How to identify merchant risk
Section 4: Statistic and ML
Lecture 16 Stats outline
Lecture 17 Hypothesis
Lecture 18 Sampling
Lecture 19 Sample Size Calculation
Lecture 20 Confusion Metrix
Lecture 21 ML Basic
Lecture 22 Linear Regression 101
Lecture 23 Linear Regression 102
Lecture 24 Linear Regression 103
Lecture 25 Linear Regression 104
Lecture 26 Logistic Regression 101
Lecture 27 Logistic Regression 102
Lecture 28 Decision Tree 101
Lecture 29 Decision Tree 102
Lecture 30 Random Forest 101
Lecture 31 Random Forest 102
Lecture 32 GBDT 101
Lecture 33 GBDT 102
Lecture 34 Xgboost 101
Lecture 35 Xgboost 102
Lecture 36 Model testing and evaluation
Section 5: SQL
Lecture 37 How to run SQL in this class
Lecture 38 where our sql examples are and how to play with them
Lecture 39 Select
Lecture 40 Select distinct
Lecture 41 where clause
Lecture 42 group by
Lecture 43 aggregate function
Lecture 44 Max/min function
Lecture 45 Having Clause
Lecture 46 Join
Lecture 47 In operator
Lecture 48 Not equal operator
Lecture 49 date function
Lecture 50 case when statement
Lecture 51 cast function
Lecture 52 Limit and offset function
Lecture 53 window function
Lecture 54 Subquery
Lecture 55 Complex Join
Lecture 56 Join and aggregate functions
Lecture 57 combine having and where
Lecture 58 Duplicates
Lecture 59 Nth number
Lecture 60 Previous Date/record
Lecture 61 Query Efficiency
Section 6: Python
Lecture 62 Python input and output
Lecture 63 Python: Statement, Indentation and Comments
Lecture 64 Python: Data type
Lecture 65 Python: functions
Lecture 66 Python: operator
Lecture 67 Python: if else
Lecture 68 Python: for loop
Lecture 69 Python: while loop
Lecture 70 Python: List 101
Lecture 71 Python: List 102
Lecture 72 Python: Tuple 101
Lecture 73 Python: Tuple 102
Lecture 74 Python: Set 101
Lecture 75 Python: Set 102
Lecture 76 Python: Dictionary 101
Lecture 77 Python: Dictionary 102
Lecture 78 Python: numpy 101
Lecture 79 Python: numpy 102
Lecture 80 Python: numpy 103
Lecture 81 Python: numpy 104
Lecture 82 Python: Pandas 101
Lecture 83 Python: Pandas 102
Lecture 84 Python: Pandas 103
Lecture 85 Python: Pandas 104
Lecture 86 Python: Pandas 105
Lecture 87 Python: matplotlib 101
Lecture 88 Python: matplotlib 102
Lecture 89 Python: scikit-learn 101
Section 7: Case study
Lecture 90 First Case Study: Nashville Housing Overview
Lecture 91 Thinking process
Lecture 92 Nashville Housing Overall Trend
Lecture 93 Nashville Housing analysis
Lecture 94 Nashville Housing Summary
Lecture 95 Second Case Study: Subscription business model analysis
Lecture 96 Overall business performance
Lecture 97 Load Subscription business data into dataframe
Lecture 98 Build a decision tree model in Python to improve business performance
Section 8: Congratulations
Lecture 99 Congratulations!
Beginners who want to start a career in Payment & Payment Risk,Beginners who want to do payment risk and fraud analytics,Beginners who want to do payment risk and fraud data science,Anyone who is passionate about mitigating risk and catch fraud with data