Log into E-learning courses powered by IDEC

DIFME: Digital Internationalisation and Financial Literacy Skills for micro entrepreneurs

Piloting/Testing and Dissemination of DIFME skillsets

This DIFME (sister to InvestProject) module shares with delegates skills relating to performing data manipulation, data analysis and data visualization to effectuate appropriate business intelligence for micro-entrepreneurs. This portal was set up to assist in the piloting, testing and dissemination of key DIFME skillsets that align to

Digital skills and competence, and digital and online learning

European Framework for the Digital Competence of Educators: DigCompEdu

Coordinated Plan on Artificial Intelligence "Made in Europe"

and reflect key skills identified in the DIFME survey see below:

This portal was designed to help pilot/test and disseminate digitization and financial literacy skills pertinent to Business Intelligence/Data Analytics. In line with European framework for Digital skills we encourage micro-entrepreneurs to use this resource which will be updated to reflect local needs of stakeholders: newcomers/explorers/integrators/experts/leaders/pioneers. By extracting Business Intelligence from commercial data - stakeholders can make superior data-driven decision making. No prior skill set is assumed here on the portal. Step-by-step instruction from scratch is provided here with audio-visual demonstration of key concepts. We do not assume any prior expertise in this field , yet, we expect users of the portal should emerge with a working knowledge of basics and be in a position to develop further once completing this module. Essential to framing Business Intelligence are data query and data transformation. This course introduces these techniques and concepts linked to business intelligence, data analytics and machine learning in a hands-on/learn-by-doing style. This module will help decision makers use analytics to formulate and support them in solving business problems and communicate that analysis to key stakeholders. Importantly, the module relies on using Freeware: R/RStudio/RStudio Cloud and Nearware (nearly everybody has it anyway): Excel. The reading materials, code and other learning tools are all non-subscription based. This is important for removing barriers to entry and making learning tools available to EU citizens as widely as possible during the current period of Economic upheaval. RStudio Cloud resources can be widely accessible from phone, tablet or computer - so hardware equally should not be a barrier to entry. This course is designed to permit delegates to leverage as fully as possible many extra-ordinary resources for free.

Learning Outcomes

Data Analytics Tools

Develop a broad insight and understanding of data analytics tools and the ability to extract useful knowledge from data. Develop business intelligence from Machine Learning techniques. Demonstrate how Artificial Intelligence can be deployed to assess mortgage applicants. Introduce delegates to state of the art Cloud Resources free to micro-enterprises.

Statistical Analysis

Develop a mastery of basic statistical techniques - important for leveraging IBM Watson Studio and R/RStudio/RStudio Cloud tools. Basic frameworks like the Normal Distribution and student-t distribution are introduced. Basic OLS modeling also introduced to develop Business Intelligence.

Excel and some practical VBA

Develop basic data analysis in Excel and VBA. We demonstrate how to implement OLS modeling in Excel. Also we provide some training from scratch on how to automate the estimation of mortgage repayments using VBA. (If Excel is not your thing - no problem use Javascript in Googlesheets).

Visualisation

Delegates will be introduced to GGPLOT2, created by Hadley Wickham, and will be trained to create publication quality plots with minimal amounts of adjustments, tweaking and zero cost. Ideal for micro-entrepreneurs. GGPLOT2 is introduced and explained to delegates from scratch. The widely acclaimed package is one of the leading R tools for producing “elegant graphics for data analysis”. GGPLOT2 plotting makes it simple to create complex graphs for data frames with a more programmatic and intuitive interface specifying what variables to plot, how they are displayed, and general visual properties.

Hone your skills in R/RStudio /RStudioCloud & Python/Google Colab/Jupyter Notebook

Perform Data Analysis in RStudio/Google Colab. Develop a Data Analytical model for predicting survival on board the ill-fated Titanic . Train a Machine Learning algorithm to determine which mortgage applicants would be successful. Evaluate varying Machine Learning models using confusion matrices. Predict Wine Quality and Prices using standard regression techniques.

R is an incredibly powerful and widely used programming language for forecasting, statistical analysis and modelling but also for Visualization and Data Transformation/Data Query. These are essential for report writing, developing and disseminating business plans. In particular, the tidyverse umbrella package from R can be used to tease out many key areas of data analytics. The "tidyverse" suite assembles some of the most versatile R packages: ggplot2, dplyr, tidyr, readr, purrr, and tibble. R can be used also to touch on newer forms of statistical modelling: Machine Learning.

These tools are available seamlessly in R. We exploit the Kaggle platform - a free to use resource to access code and data. In particular, the Titanic Kaggle Dataset is presented as a sort of handy "proof of concept" for those new to Machine Learning. We also demonstrate Machine Learning and AI by training the HMDA dataset for mortgage origination and vetting. Some examples, techniques and code developed by Hal Varian (chief Economist of Google) for Machine Learning are introduced here and explained in detail.

R has some advantages in that it can be simple to implement as scores of relevant libraries exist (see: https://www.kaggle.com/rtatman/kernels & http://www.daveondata.com/ ) and web resources are widely available and fully primed to go. An interesting example for Wine Quality forecasting is set up in a Cloud Computing environment using techniques introduced by Professor Orley Ashenfelter of Princeton. We also leverage content and study materials hosted by MITOPENCOURSEWARE and disseminated freely to users. Christoph Hanck, Martin Arnold, Alexander Gerber and Martin Schmelzer have published an online text second to none for modeling techniques. We make use of that text extensively here. Also we use a number of techniques from the landmark text R for Data Science. Fortunately, these resources are all free and do not require making any purchase.

See links to some important downloads:

https://cran.r-project.org/bin/windows/base/

https://rstudio.com/products/rstudio/download/

I recommend delegates set up an account with RStudio Cloud:

https://rstudio.cloud/

// The code that is provided here is free software; you can redistribute it and/or

// modify it under the terms of the GNU General Public License

// as published by the Free Software Foundation.

// These snippets of code here are distributed in the hope that they will be useful,

// but WITHOUT ANY WARRANTY; without even the implied warranty of

// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the

// GNU General Public License for more details.

// http://www.fsf.org/copyleft/gpl.html

Useful Installations