week 7 - data analytics + business intelligence Flashcards
what is meant by data analytics?
process of collecting, cleaning, inspecting, transforming, storing + querying data. This is relied on heavily by business intelligence.
what are the purposes of data analytics?
- convert + clean raw data into actionable insights.
- identifies past patterns + uses this to forecast future occurrences.
- carries out data mining tasks + algorithm development.
- preserves analysts + computer programmers who have a technical focus.
what is meant by business intelligence?
combines architectures, tools, databases, analytical tools, application + methodologies that convert unprocessed data into valuable insights.
what are the purposes of business intelligence?
- supports decision making using insights.
- looks back at the past + uses this to inform future strategy.
- used by leadership teams + non technical personnel.
- relies on clean dashboards, reporting + other monitoring techniques to relay insights in a clear + easily consumable way.
what are the characteristics of changing business environments?
- increased hardware, software + network capabilities.
- analytical support, group communication + collabs.
- overcoming cognitive limits in processing + storing info.
- improved data + knowledge management.
- managing giant data warehouses + big data.
- anywhere, anytime support.
how does business intelligence give a business a competitive advantage?
- improved decision making: data driven insights enable businesses to anticipate market trends.
- personalisation + customer experience: ai powered recommendation systems tailor user experiences.
- operational efficiency: predictive maintenance prevents costly equipment failures.
- fraud detection + risk management: ai driven analytics identify suspicious transactions + fraud patterns.
what is an example + the impact of improved decision making for giving a business competitive advantage?
Example: retailers use BI to analyse customer purchase patterns.
Impact: reduces stockouts + excess inventory costs.
what is an example + the impact of personalisation + customer experience for giving a business competitive advantage?
Example: netflix + amazon leverage bi to suggest relevant content/products.
Impact: increase customer engagement + sales conversions.
what is an example + the impact of operational efficiency for giving a business competitive advantage?
Example: manufacturers use sensors to detect issues before breakdowns.
Impact: reduces downtime + maintenance costs.
what is an example + the impact of fraud detection + risk management for giving a business competitive advantage?
Example: banks use bi to flag unusual activity in customer accounts.
Impact: improves security, minimises financial losses + enhances compliance.
what is a database?
organised collection of data, stored electronically for easy retrieval.
what is the importance of databases?
stores + manages large scale business data, enables fast retrieval of structured info, allows for data driven decision making.
what are the types of databases in analytics?
- relational database sql
- non relational database nosql
what is a relational database (sql)?
structured way of storing data in tables where relationships exist between data points, it follows the relational model.
what are the features of relational databases?
- data is stored in tables (relations).
- each row is a record (tuple).
- each column is an attribute (field).
- uses primary + foreign keys to establish relationships.
what are non-relational databases?
flexible data storage system that does not use structured tables + fixed schemas.
what are non-relational databases designed for?
- scalability.
- performance.
- handling large volumes of unstructured data.
what is meant by data quality?
a measure of how well data meets its intended purpose. poor data can lead to incorrect decisions.
what are the common issues regarding real world data?
- missing values.
- duplicates.
- outliers.
- inconsistent formats.
what are the key dimensions of data quality?
- accuracy.
- completeness.
- consistency.
- timeliness.
- validity.
what is meant by big data?
high volume, velocity + variety info assets that demand cost-effective, innovative forms of info processing for enhanced insight + decision making.
what do those 3 v’s mean in the definition of big data?
- volume: size of data.
- velocity: how fast new data is generated.
- variety: many different forms (text, image, audio, video).
what is meant by a data lake?
a centralised storage system that holds large amounts of data in its original format.
moves the burden of data cleaning + integration to later stages.
what is hadoop?
an open source framework that’s popular for distributed storage + parallel processing of massive amounts of data, spreading the data over a large cluster of machines.
what is mapreduce?
a programming model that allows for large batch-processing jobs to be divided into smaller tasks that can be run in parallel.
what are the different types of business analytics?
- descriptive
- predictive
- prescriptive
what are descriptive analytics?
they examine historical data to identify patterns, trends + insights.
what is the purpose of descriptive analytics?
helps orgs understand what happened by summarising past data.
what are the different sources of data of descriptive analytics?
- transactional databases.
- crm systems.
- sales reports.
- website traffic logs.
what are the features of descriptive analytics?
- historical data analysis: examines past performance + trends.
- data aggregation + summarisation: converts raw data into meaningful insights.
- data visualisation: uses charts, graphs + dashboards for better interpretation.
- performance measurement: tracks kpi’s over time.
what are examples of descriptive analytics in business?
Retail: sales reports showing monthly revenue trends.
Healthcare: patient admission statistics over the last five years.
Marketing: website traffic analytics showing user engagement.
Finance: monthly expense + revenue tracking.
what are predictive analytics?
uses statistical models, machine learning + ai to analyse past data + forecast future trends?
what is the purpose of predictive analytics?
helps orgs anticipate what is likely to happen based on historical patterns.
what are the key techniques used in predictive analytics?
- regression analysis.
- machine learning.
- neural networks.
what are the key features of predictive analytics?
- trend forecasting: uses historical data to predict future outcomes.
- machine learning + ai: applies advanced algorithms to detect hidden patterns.
- risk management: identifies potential risks before they occur.
- decision support: helps businesses make proactive, data-driven decisions.
what are examples of predictive analytics in business?
Retail: forecasting customer demand to optimise inventory.
Healthcare: predicting disease outbreaks based on historical patient data.
Marketing: ai driven customer churn prediction.
Finance: fraud detection using anomaly detection models.
what are prescriptive analytics?
help businesses make data-driven decisions by providing specific recommendations based on past data + predictions.
what is the purpose of prescriptive analytics?
they suggest the best course of action instead of analysing what happened or predicting what will happen.
what are the data sources used with prescriptive analytics?
- customer transactions.
- market trends.
- operational data.
- external datasets.
what are the features of prescriptive analytics?
- decision optimisation: recommends the best action for the given scenario.
- ai + machine learning integration: learns from data to improve decision making.
- scenario analysis: evaluates multiple possible outcomes before suggesting the best outcome.
- automated decision making: reduces human intervention by automating complex decisions.
what are the challenges of big data analytics?
- data quality + accuracy: inconsistent, incomplete affecting decision making.
- data storage + management: handling large vols of structured + unstructured data is complex.
- processing speed: analysing real time data requires high performance computing.
what are more challenged of big data analytics?
- integration issues: combining data from multiple sources can be hard.
- security + privacy issues: protecting sensitive data from breaches.
- cost of infrastructure: high investment needed for cloud storage, data processing + analytics tools.
