Introduction to Data Analytics for Accountants

Explore data analytics for accountants and finance professionals, surveying digital skills, data structures beyond spreadsheets, analytics types, tools, and applications like outlier detection, sentiment analysis, and predictive models.

Explore structured, unstructured, and semi-structured data with examples from Excel sheets, ERP, payroll, and web content, and note that unstructured data dominates today's data landscape.

Explore how data analytics turns raw data from many sources into insights and decisions, through descriptive, diagnostic, predictive, and prescriptive analytics.

Understand how data volume and unstructured data shape analytics; master the analytics process from question formation, data wrangling (acquisition and cleaning), and exploration to communicating findings with visualizations.

Identify and interpret outliers in large data sets, understand their impact on audits, and recognize how sampling may miss suspicious transactions, guiding a more focused investigation.

Explore how to identify outliers using box-and-whisker plots on Enron executive bonuses and salaries, applying the five-number summary and Excel formulas to spot higher and lower outliers.

Apply a box-and-whisker plot to detect outliers in a vehicle repair and maintenance ledger, focusing on the Total column and a thirty-five thousand data point indicating an incorrect vehicle purchase.

Learn how to extract sentiment from customer reviews, mapping positivity and negativity to KPIs for accountants, and apply an Excel-based example to real text data.

Learn to perform sentiment analysis on Amazon product reviews using Excel with the Azure Machine Learning Studio plugin, analyzing review text to classify sentiment as positive, negative, or neutral.

Use R to perform deep sentiment analysis on an Excel dataset, visualizing emotions like joy and anger. Identify product features driving positive or negative reviews to guide improvements.

Analyze Melbourne housing market data set with Excel regression using the data analysis toolpak; clean data by removing missing values and non-numeric fields, then set x and y input ranges.

Run an Excel regression to predict property price using rooms, distance from CBD, bathrooms, car spaces, and land size; assess with R-squared and p-values, and validate with a real example.

Prescriptive analytics uses machine learning to learn from features and labels, train on past data, and recommend a course of action such as buy, sell, or hold.

Prescriptive analytics lecture uses a Jupiter notebook with Yahoo Finance data and Brownian motion to forecast 60-day stock prices and recommends buy, hold, or sell with logistic regression insights.

Encourage accountants and finance professionals to start developing digital skills now, as data analytics remains in early stages, and choose your part to continue building new competencies.