Introduction to Big Data TechniquesLocked: included in All Access

How fintech is changing investment analysis: what makes data 'Big', where alternative data come from and what can go wrong with them, how machine learning learns (and overfits), the main types of ML, how data scientists process and display data, and how text analytics and NLP turn words into investment signals.

1. 1. Fintech and the four Vs of Big DataFintech gives analysts two things, far more data and smarter tools to read it, and Big Data is defined by its volume, velocity and variety, plus veracity once it is used to predict.Locked: included in All Access12 min
2. 2. Sources of Big Data and its challengesAlternative data from individuals, business processes and sensors can reveal performance before traditional reports do, but they are messy, can be biased and may raise legal and ethical problems.Locked: included in All Access13 min
3. 3. AI and how machine learning learnsAI systems do tasks that once needed human intelligence; machine learning, the key AI tool for Big Data, learns structure from large datasets without assuming a distribution, using separate training, validation and test data.Locked: included in All Access12 min
4. 4. Overfitting, underfitting and model fitA useful ML model learns the true signal: overfit models memorise noise and fail on new data, underfit models miss real patterns, and comparing training with test performance tells you which you have.Locked: included in All Access11 min
5. 5. Supervised, unsupervised and deep learningSupervised learning learns from labelled examples to predict, unsupervised learning finds structure in unlabelled data, and deep learning uses many-layered neural networks, with either approach, to recognise complex patterns.Locked: included in All Access12 min
6. 6. Data science: processing and visualisationData scientists turn raw Big Data into usable information through five processing steps (capture, curation, storage, search and transfer) and then display it with visual tools that fit the data's structure.Locked: included in All Access12 min
7. 7. Text analytics, NLP and data science toolsText analytics and NLP let machines read filings, call transcripts, news and central bank speeches at a scale no team can, picking up sentiment shifts and short-term indicators early; data scientists build them with languages such as Python and R and databases such as SQL and NoSQL.Locked: included in All Access14 min