Machine learning with Python for finance professionals

ACCA via edX

Go to class Write review

Details

Go to class

Provider

edX
Pricing

Free Online Course (Audit)
Languages

English
Certificate

$199.00 Certificate Available
Duration & workload

5 weeks, 4-5 hours a week
Sessions

On-Demand
Level

Intermediate
Subtitles

English

Found in

Part of

FinTech for Finance and Business Leaders

Overview

Welcome to Machine learning with Python for finance professionals, provided by ACCA (Association of Chartered Certified Accountants), the global body for professional accountants. This course is part of the FinTech for finance and business leaders professional certificate program.

This course will provide a view of what lies under the surface of a machine learning output, help to better interrogate a model, and partner with data scientists and others in an organisation to drive adoption and use of machine learning. Digital finance knowledge and skills are essential components of the technology transformation as business becomes increasingly customer focused. And having the skills to understand how these technologies are deployed and integrated into a customer centric business strategy is essential. With 16 Jupyter Notebooks available, alongside corresponding solution notebooks, and bonus exercises you will quickly become skilled in specific time-saving Machine Learning tools

Access to all end of module quizzes
Access to the final assessment

Syllabus

Module 1 – Introduction to Python

In this module, the fundamental principles of coding are introduced using the Python programming language. From taking your first steps in coding to understanding data types to control flows, this module provides the essential elements needed for coding in Python.

Topics covered: ****

● Introduction to the Python programming language

● Using the Jupyter Notebook environment to run Python code

● Data types: strings, integers and floats; how information is created in Python

● Variables and containers: how information is stored in Python

● Mathematical operators and calculation in Python

● Control flows, logic and writing functions: how to automate processes using code.

Module 2 – Python for Data Analysis ****

Learn the basics of using Python for working with data. This module introduces pandas, a Python library that is widely used for powerful yet easy data manipulation. Learn to load data from different sources, drill down and segment, create pivot table style aggregations and explore various data visualisation libraries.

Topics covered: ****

● Introduction to working with third-party Python packages

● Working efficiently with large datasets using NumPy for numerical analysis

● Using pandas to read in, manipulate and analyse data

● Data visualisation using matplotlib and Seaborn

● Merging datasets and techniques for handling missing data.

Module 3 – Automating Excel using Python ****

Automation helps businesses to make regular reporting more efficient. In this module you will learn to automate commonly repeated Excel workflows using the xlwings Python library. Learn how to control Excel from Python and create template reports that update live with the latest data.

Topics covered :

● Introduction to xlwings: a Python library for interacting with live Excel spreadsheets

● Using pandas and xlwings to automate the generation of Excel-based business intelligence reporting

● Learn to automate Excel and give your Excel-based workflows access to the full power of the Python data scientific ecosystem of tools

Module 4 *– * Machine learning with Python

Introductory hands-on module covering the essentials of implementing a real-world machine learning project. Understand the basics of ML theory and its relationship to data science, Big Data and Artificial Intelligence.

Topics covered:

Build a classifier algorithm for RFM modelling
Build a machine learning system for category classification using decision trees, random forests and natural language processing
Learn how to evaluate and tune machine learning algorithms, and how to prevent overfitting using cross-validation.