Data Science Vocabulary Quiz
12 multiple-choice questions on data science vocabulary: datasets, regression, clustering, overfitting, bias and model validation. B2–C1 level.
This quiz focuses on how the target vocabulary for Data Science is actually used in context at B2–C1 level, rather than testing bare definitions. Correct answers you will need to identify include terms such as dataset, regression, clustering, overfitting and feature, each embedded in a full example sentence so you have to judge meaning from context, not just recognise an isolated word.
Working through all 12 questions and checking the explanations in the FAQ below is a quick way to spot any terms you are still unsure of. Revisiting the quiz again after a day or two, rather than only once, is one of the most reliable ways to move new vocabulary from passive recognition into words you can use confidently yourself in speaking and writing.
Keep building your data science vocabulary.
Data Science Vocabulary — FAQ
What is a 'dataset'?
A dataset is a structured collection of data used for analysis or for training a model. Datasets can range from small spreadsheets to enormous collections of millions of records, and their quality directly affects how reliable any conclusions or models drawn from them will be.
What is the difference between 'regression' and 'clustering'?
Regression is a statistical method for predicting a continuous numerical value, such as forecasting house prices from size and location. Clustering, on the other hand, is a method of grouping similar data points together without any predefined labels, used to discover natural groupings such as customer segments.
What does 'overfitting' mean?
Overfitting happens when a model learns the training data too closely, including its noise and quirks, so that it performs very well on that data but poorly on new, unseen data. Reducing model complexity or using more training data can help prevent overfitting.
What is a 'feature' in data science?
A feature is an individual measurable property or characteristic used as input to a model. For example, in a credit risk model, features might include a customer's age, income and postcode, all of which the model uses to make predictions.
What is the purpose of 'validation'?
Validation is the process of evaluating a model's performance on data it has not seen during training, in order to check how well it will generalise to new, real-world data. Cross-validation, which tests a model on multiple different subsets of data, is a common validation technique.
What is the difference between 'bias' and 'variance'?
Bias is a systematic error in a model that causes consistently inaccurate predictions, often because the model is too simple to capture the underlying pattern. Variance is the degree to which a model's predictions change with different training data, and high variance is a sign that a model may be overfitting.
What is a 'neural network'?
A neural network is a computational model loosely inspired by the structure of the human brain, made up of layers of connected nodes. Neural networks are widely used in machine learning tasks such as image recognition, where they can learn to identify objects with very high accuracy.
What does 'correlation' mean in data science?
Correlation is a statistical measure of how closely two variables change together, for example whether increased advertising spend tends to occur alongside increased sales. It is important to remember that correlation does not necessarily mean one variable causes the other.
What is an 'outlier'?
An outlier is a data point that is significantly different from the rest of the dataset, for example an unusually large or small value compared to everything else recorded. Outliers are sometimes genuine unusual events and sometimes the result of data entry errors, so they must be investigated carefully rather than automatically removed.
What is a data 'pipeline'?
A pipeline is an automated sequence of data processing steps that takes raw data from its source through cleaning, transformation and analysis to a final output, such as a report or a trained model. Well-designed pipelines save enormous amounts of manual repetitive work in a data science project.