TASC Data Science and Digital Solutions study plan

Map the full exam blueprint into a one-page outline listing every subtopic under Data Science and Digital Solutions.

Define the vocabulary of data science and digital solutions by writing plain-language definitions for 40 core terms.

Classify each subtopic as heavy, medium, or light based on how many practice questions it is likely to generate.

Set up a spaced-repetition deck and seed it with the first 40 term cards.

Explain the data lifecycle from collection through cleaning, storage, analysis, and reporting in your own words.

Compare structured, semi-structured, and unstructured data using three original examples each.

Distinguish descriptive, diagnostic, predictive, and prescriptive analytics with a worked example per type.

Identify which lifecycle stage each exam-style scenario question is testing.

Compute mean, median, mode, range, variance, and standard deviation by hand for three small datasets.

Interpret the meaning of each statistic in a business context rather than just reporting the number.

Explain how outliers and skewed distributions change which measure of central tendency is appropriate.

Sketch and label the parts of a normal distribution and state the empirical rule percentages.

Distinguish correlation from causation and write three examples where the confusion would mislead a decision-maker.

Interpret p-values, confidence intervals, and sample size in plain language without formulas.

Identify common sampling and survivorship biases in short scenario descriptions.

Design a simple A/B test for a stated business question, naming the metric and success threshold.

Describe supervised versus unsupervised learning and name two algorithms commonly used for each.

Explain overfitting, underfitting, training and test splits, and why holdout data matters.

Define the standard classification metrics and state when accuracy alone is misleading.

Walk through how a model moves from prototype to production monitoring in a governed way.

Explain relational versus non-relational databases and when each is the better storage choice.

Write and interpret basic SQL queries covering filtering, grouping, aggregation, and joins.

Describe how a data pipeline moves and transforms data, including ETL versus ELT.

Outline cloud storage, compute, and managed analytics services at a conceptual level.

Summarize how machine learning and generative AI are applied in business settings, with three realistic use cases.

Explain data privacy, consent, retention, and access-control obligations in general terms.

Identify governance roles and the purpose of a data catalog and lineage tracking.

Evaluate two short case studies for ethical risk and recommend a mitigation for each.

Synthesize all prior weeks into a single condensed review sheet of no more than four pages.

Complete a timed 50-question mixed practice set and log every missed item by subtopic.

Re-study the three weakest subtopics and re-answer the missed items until correct.

Rehearse explaining five key concepts aloud in under two minutes each.