Skip to content
Edition NigeriaGlobal
Country: Denmark

You are in the Denmark edition. Type your country to switch.

Set up your profile

You are learning in the Denmark edition, with examples in kroner and from Denmark.

Learning path

Financial data & analytics

The maths, data and spreadsheet skills behind markets: percentages, averages and probability, then clean data, returns, risk and honest charts.

43 lessons · about 10.8 hours · Not started

Start the path

Beginner

  1. Financial data & analyticsPercentages and percentage pointsRead nowPercentages and percentage pointsFinancial data & analytics · Beginner · 15 min

    A percentage is a share of a hundred. A percentage point is the gap between two percentages. Mixing them up, or forgetting that losses and gains are not symmetrical, is behind many misleading headlines.

  2. Financial data & analyticsCompounding and CAGRRead nowCompounding and CAGRFinancial data & analytics · Beginner · 15 min

    The compound annual growth rate, or CAGR, is the single steady yearly rate that would take you from a starting value to an ending value. It is the honest way to describe growth over several years, and it is usually lower than the simple average of yearly returns.

  3. Financial data & analyticsAverages: mean, median and modeRead nowAverages: mean, median and modeFinancial data & analytics · Beginner · 15 min

    The mean, the median and the mode are three ways to describe a typical value. In finance, a few very large values often pull the mean far from what is typical, so knowing which average you are looking at matters.

  4. Financial data & analyticsSpread and volatility: how much …Read nowSpread and volatility: how much values varyFinancial data & analytics · Beginner · 15 min

    Two investments can have the same average return and very different journeys. Range, percentiles and the standard deviation describe how widely values spread around the average, and volatility is the standard deviation of returns.

  5. Financial data & analyticsProbability and expected valueRead nowProbability and expected valueFinancial data & analytics · Beginner · 15 min

    Probability measures how likely something is, from 0 to 1. Expected value weighs each possible outcome by its probability and adds them up. It is the right way to think about uncertain bets, as long as you also ask whether you could survive the bad outcomes.

  6. Financial data & analyticsReading tables, charts and log s…Read nowReading tables, charts and log scalesFinancial data & analytics · Beginner · 15 min

    Tables and charts are only as clear as their labels. Check the units, the period and the axes first. On long price charts a logarithmic scale shows equal percentage moves as equal heights, which makes decades of growth readable.

Intermediate

  1. Financial data & analyticsFinancial data sourcesRead nowFinancial data sourcesFinancial data & analytics · Intermediate · 15 min

    Financial data comes in families: market prices, company fundamentals, macroeconomic statistics, regulatory filings and alternative data. Each has a primary source, a typical delay and typical errors, and good analysis starts by knowing which is which.

  2. Financial data & analyticsFree against paid data, licensin…Read nowFree against paid data, licensing and terms of useFinancial data & analytics · Intermediate · 15 min

    Free to view is not free to reuse. Market data, index values and many datasets come with licences that limit copying, publishing and commercial use. Reading the terms before you build on data saves trouble later.

  3. Financial data & analyticsCleaning data for splits, divide…Read nowCleaning data for splits, dividends and ticker changesFinancial data & analytics · Intermediate · 15 min

    Raw prices jump on the day of a split, a bonus issue or a large dividend, even though no investor gained or lost. Adjusting history with a factor removes these false moves, and tracking ticker changes keeps one company's history together.

  4. Financial data & analyticsSurvivorship, missing data, time…Read nowSurvivorship, missing data, time zones, calendars and currenciesFinancial data & analytics · Intermediate · 15 min

    A dataset can be clean line by line and still mislead. Companies that disappeared, gaps for holidays, prices taken at different times in different time zones and mixed currencies all distort results unless you handle them deliberately.

  5. Financial data & analyticsReturns, CAGR and volatility in …Read nowReturns, CAGR and volatility in a spreadsheetFinancial data & analytics · Intermediate · 15 min

    With a column of prices you can calculate daily or monthly returns, the compound growth rate and volatility in a few formulas. Building them yourself shows exactly what a returns figure means and what it leaves out.

  6. Financial data & analyticsDrawdowns and correlation in a s…Read nowDrawdowns and correlation in a spreadsheetFinancial data & analytics · Intermediate · 15 min

    A drawdown measures how far a value has fallen from its last peak, and correlation measures how closely two sets of returns move together. Both take a few columns in a spreadsheet and tell you more about risk than volatility alone.

  7. Financial data & analyticsPivot tables for financial dataRead nowPivot tables for financial dataFinancial data & analytics · Intermediate · 15 min

    A pivot table turns a long list of rows, such as trades, dividends or daily returns, into a summary by category and period in a few clicks. It works best on tidy data: one row per record and one column per field.

  8. Financial data & analyticsCharts done right, and spotting …Read nowCharts done right, and spotting misleading chartsFinancial data & analytics · Intermediate · 15 min

    A chart can be accurate in every number and still mislead through a cut axis, a chosen start date, two different axes or a missing adjustment. Knowing the common tricks lets you build honest charts and question the ones you see.

  9. Financial data & analyticsDistributions and fat tailsRead nowDistributions and fat tailsFinancial data & analytics · Intermediate · 15 min

    Market returns have a shape as well as an average and a spread. Extreme days happen far more often than a bell curve predicts, and the long tail is often on the loss side, so risk measures built on normal returns understate how bad a bad day can be.

  10. Financial data & analyticsRegression and betaRead nowRegression and betaFinancial data & analytics · Intermediate · 15 min

    A regression fits the line that best describes how a share's returns move with the market's. Its slope is beta, the share's average sensitivity to market moves, and R-squared shows how much of the share's movement the market explains. Beta is an estimate that changes with the data choices behind it.

  11. Financial data & analyticsCorrelation against causationRead nowCorrelation against causationFinancial data & analytics · Intermediate · 15 min

    Two series can move together without either one causing the other. Common causes, reverse causation, shared trends and plain chance all produce correlation, so claims that one thing drives share prices need a mechanism, the right timing and fresh evidence.

  12. Financial data & analyticsSignificance and data-miningRead nowSignificance and data-miningFinancial data & analytics · Intermediate · 15 min

    Significance tests ask how surprising a result would be if there were nothing real behind it. Noisy market returns mean short track records prove little, and testing many ideas always produces some lucky winners, so every variation tried counts as a test.

  13. Financial data & analyticsRatio analysis at scaleRead nowRatio analysis at scaleFinancial data & analytics · Intermediate · 15 min

    Calculating ratios for many companies at once is mostly about consistency: the same definitions, periods, currency, units and formula in every row. Negative denominators, outliers and sector differences then need deliberate handling before companies can be compared.

  14. Financial data & analyticsScreening shares with dataRead nowScreening shares with dataFinancial data & analytics · Intermediate · 15 min

    A stock screen applies written rules to a universe of companies to produce a short list worth researching. Good screens start from a question, use a few stated filters and, when tested on the past, use point-in-time data and include companies that later disappeared.

  15. Financial data & analyticsPeer comparisonRead nowPeer comparisonFinancial data & analytics · Intermediate · 15 min

    Relative valuation compares a company's multiples with those of genuine peers. The result depends on choosing the right peers, using the median, converting enterprise multiples back to equity with net debt, and explaining any gap through growth, risk and earnings quality.

  16. Financial data & analyticsBuilding a simple valuation mode…Read nowBuilding a simple valuation model from dataFinancial data & analytics · Intermediate · 15 min

    A simple valuation model turns stated assumptions into a value range. Separate inputs, history, forecast, valuation and checks; derive a few drivers from cleaned data; value next year's free cash flow with a constant-growth formula; cross-check with peers; and show the sensitivity.

Advanced

  1. Financial data & analyticsLab 1: reading CSV files in Pyth…Read nowLab 1: reading CSV files in Python and SQLFinancial data & analytics · Advanced · 15 min

    A CSV file is the plain-text table most financial data arrives in. This lab shows how to load one into Python with pandas and into a SQLite database, check that it loaded correctly, and catch the usual problems: dates read as text, thousands separators, missing values and duplicated rows.

  2. Financial data & analyticsLab 2: computing returns in codeRead nowLab 2: computing returns in codeFinancial data & analytics · Advanced · 15 min

    This lab turns a column of prices into daily returns, cumulative returns, annualised volatility and maximum drawdown in Python, and shows how to check every figure against a hand calculation on a small invented sample. It also explains simple against log returns and why returns must be computed per ticker.

  3. Financial data & analyticsLab 3: plotting prices and returnsRead nowLab 3: plotting prices and returnsFinancial data & analytics · Advanced · 15 min

    This lab draws the four charts most analysis needs, using matplotlib: a price line, two shares rebased to 100, a histogram of returns and a drawdown chart. It applies the honest-chart rules in code: labelled axes, stated sources and dates, log scales for long periods and no truncated bar axes.

  4. Financial data & analyticsLab 4: SQL on a price tableRead nowLab 4: SQL on a price tableFinancial data & analytics · Advanced · 15 min

    This lab builds a small price table in SQLite and answers real questions with SQL: filtering by date and ticker, averages with GROUP BY, joining a company table, and computing daily returns with the LAG window function. Every query is checked against invented data you can verify by hand.

  5. Financial data & analyticsLab 5: cleaning corporate action…Read nowLab 5: cleaning corporate actions in codeFinancial data & analytics · Advanced · 15 min

    This lab adjusts a raw price series for a share split and a dividend in Python, using an adjustment factor applied to every earlier price, then checks the result: no false jump on the split date and a total return that matches a hand calculation. It also handles a ticker change by mapping old and new symbols to one identifier.

  6. Financial data & analyticsLab 6: a sentiment classifier on…Read nowLab 6: a sentiment classifier on sample headlinesFinancial data & analytics · Advanced · 15 min

    This lab builds the simplest possible sentiment classifier, a word list that scores invented headlines as positive or negative, and measures it honestly with a confusion matrix, accuracy and precision. It then shows where word counting fails: negation, finance-specific meanings and headlines that are neutral.

  7. Financial data & analyticsLab 7: watching a model overfitRead nowLab 7: watching a model overfitFinancial data & analytics · Advanced · 15 min

    This lab fits models of rising complexity to invented data and watches the error on the training data fall while the error on held-back test data first falls and then rises. That turn is overfitting. It also shows how trying many rules on one data set produces a winner by luck alone.

  8. Financial data & analyticsLab 8: writing the model card an…Read nowLab 8: writing the model card and a reproducible notebookFinancial data & analytics · Advanced · 15 min

    The lab ends with two documents that make work trustworthy: a notebook someone else can rerun from scratch and get the same numbers, and a model card that states what the model is for, its data, its test results and its limits. Fixed seeds, pinned library versions and recorded data sources do most of the work.

  9. Financial data & analyticsBuilding a three-statement modelRead nowBuilding a three-statement modelFinancial data & analytics · Advanced · 15 min

    A three-statement model forecasts the income statement, balance sheet and cash-flow statement together from a short list of drivers. The statements are linked so that profit flows into equity, cash flows into the balance sheet, and the balance sheet balances in every period. That check is what makes the model trustworthy.

  10. Financial data & analyticsBuilding a DCF in a modelRead nowBuilding a DCF in a modelFinancial data & analytics · Advanced · 15 min

    A DCF built on a three-statement model takes each year's unlevered free cash flow, discounts it at the weighted average cost of capital, adds a terminal value and bridges from enterprise value to equity value per share. Each step has conventions that change the answer, so each must be visible and explained.

  11. Financial data & analyticsScenarios and sensitivities in a…Read nowScenarios and sensitivities in a modelFinancial data & analytics · Advanced · 15 min

    A model should show a range, not a point. A scenario switch moves the whole model between consistent sets of assumptions, sensitivity tables show how the answer changes with one or two inputs, and a tornado chart ranks which inputs matter most. The mechanics must be built so that every case runs through the same formulas.

  12. Financial data & analyticsChecking a financial modelRead nowChecking a financial modelFinancial data & analytics · Advanced · 15 min

    Checking a model means testing that it is built correctly, that its numbers make economic sense and that someone else can follow it. Built-in checks catch mechanical errors, ratio and history comparisons catch nonsense, and a structured review by a second person catches what the builder cannot see.

  13. Financial data & analyticsCommon financial modelling errorsRead nowCommon financial modelling errorsFinancial data & analytics · Advanced · 15 min

    Most modelling errors are ordinary: a typed-in number, a wrong sign, mixed units or currencies, a range that stops too soon, double counting, or a terminal value that assumes the impossible. Several widely reported cases show that such errors can change public decisions and cost firms heavily.

  14. Financial data & analyticsPresenting a financial modelRead nowPresenting a financial modelFinancial data & analytics · Advanced · 15 min

    A model is useful only if decision-makers understand what it says and how much to trust it. A good presentation starts with the answer and its range, shows the few assumptions that drive it, explains the risks and limits, and lets readers trace any number back to its source.

  15. Financial data & analyticsPerformance attribution: where t…Read nowPerformance attribution: where the return came fromFinancial data & analytics · Advanced · 15 min

    A fund beat its benchmark by 1.6 percentage points. Was that because it held more of the right asset classes, or because it picked better securities within them? Performance attribution splits the active return into allocation, selection and interaction effects. This lesson works through the standard method on an invented fund.

  16. Financial data & analyticsSharpe, Sortino and benchmark co…Read nowSharpe, Sortino and benchmark comparisonFinancial data & analytics · Advanced · 15 min

    Return alone says little about how a portfolio was managed. The Sharpe ratio measures return per unit of total volatility, the Sortino ratio counts only harmful downside moves, and the information ratio measures active return per unit of tracking error against a benchmark. This lesson computes all three on invented data and shows when each one misleads.

  17. Financial data & analyticsVaR and tracking error: methods …Read nowVaR and tracking error: methods and limitsFinancial data & analytics · Advanced · 15 min

    Value at risk estimates a loss that should be exceeded only rarely; tracking error measures how far a portfolio's returns wander from its benchmark. This lesson computes both on invented data with the main methods, parametric, historical and simulation, shows how to scale them over time, and explains where each breaks down.

  18. Financial data & analyticsMoving averages and seasonality …Read nowMoving averages and seasonality in financial dataFinancial data & analytics · Advanced · 15 min

    Monthly sales, card spending, traffic and prices are noisy and often seasonal. Moving averages smooth the noise, and seasonal indices and year-on-year comparisons separate the pattern that repeats every year from real change. This lesson shows the methods on invented data, the lag that smoothing adds and the trap of seasonal patterns found by data-mining.

  19. Financial data & analyticsforecasts fail, and stating unce…Read nowWhy forecasts fail, and stating uncertainty honestlyFinancial data & analytics · Advanced · 15 min

    Forecasts of growth, inflation, earnings and prices are often wrong, and the mistake is rarely the point estimate alone; it is the false confidence around it. This lesson explains why forecasts fail, from regime change to feedback, and how to state uncertainty honestly with ranges, probabilities, fan charts and calibration checks.

  20. Financial data & analyticsDashboards and performance repor…Read nowDashboards and performance reports that communicateFinancial data & analytics · Advanced · 15 min

    A dashboard or performance report succeeds when the reader understands the situation in seconds and can trust every number. This lesson covers choosing the few measures that matter, giving each context, showing time, source and freshness, avoiding misleading visuals, and ends with an automatically graded performance-report task on an invented fund.

  21. Financial data & analyticsData governance: licences, linea…Read nowData governance: licences, lineage, market-sensitive data and model riskFinancial data & analytics · Advanced · 15 min

    Financial firms depend on data they may not own, cannot always verify and sometimes must not share. Data governance sets who owns each dataset, where it came from, what the licence allows, how quality is checked, who may see market-sensitive data and how models built on it are controlled. This lesson brings those threads together.

English