Flashcards
BIR
Flashcards do conjunto (31)
- 11 - Definition Business IntelligenceBusiness Intelligence are the processes, technologies, and tools needed to turn
data into information, information into knowledge, and knowledge into plans
that drive profitable business action. It encompasses data warehousing, business
analytics tools, and content/knowledge management - 22 - Def Big DataBig data is high-volume, high-velocity and/or high-variety information assets that demand cost-effective, innovative forms of information processing that enable enhanced insight, decision making, and process automation.
- 32 - Big Data - 5V• Volume
• Variety
• Velocity
• Veracity
• Value - 42 - Terms: Data MiningProcess of discovering interesting patterns and knowledge from large amounts of data.
- 52 - Terms: Machine LearningField of study that gives computers the ability to learn without being explicitly programmed
- 62 - Terms: Data Lakelarge repository of enterprise-wide data in raw format
- 72 - terms: Dark datadata that is gathered and processed by enterprises not used for any meaningful purposes (~60-90% of all data in an enterprise)
- 82- terms: IoTinterconnection of computing devices in embedded objects (sensors, wearables, cars, fridges etc.)
- 92 - Internal and external sources for structured data• internal: CRM, Point of Sale, Service Tickets
• external: Industry research data, financial market data - 102 - Internal and external sources for structured data• internal: Email, Call-Center transcripts, forums, blogs,
• external: Social networks, forums, blogs, videos - 112 - Big Data Tech - Cloud ComputingUsing a ‘cluster’ of pooled resources of multiple (remote) servers
- 122 - Descr HadoopOpen source software framework that consists of a Hadoop Distributed File
System (HDFS) - 132 - Descr Map REduceProgramming model:
• Map: break up big datasets into pieces and distribute data across different
computers
• Reduce: collect results and ‘reduce’ them into one report - 142 - Descr Apache Spark• Open-source cluster-computing framework
• In-memory data processing engine - 152 - Dewscr NoSQL• Uses different data structures other than relational databases (e.g. key-value
store, document store, graph, etc.)
• Various databases: e.g. MongoDB, Cassandra, SAP Hana, Oracle NoSQL Database - 162 - Def Big Data AnalyticsBig data analytics describe software solutions which are designed to handle the attributes of big data.
- 172 - Def Digital MarketingIt is a tech-based, two-way marketing approach that acts as a decision tool involving and
anticipating customers‘ wants and needs. (Adam Sarner, Gartner Research)
In simple terms:
Digital marketing is where marketing meets the internet and other forms of new media, such as
cell phones and even video games. - 182 - Def Data-driven MarketingData-driven marketing is collecting, analysing, and executing on insights from structured and multi-structured data (for example big data) across the enterprise to drive customer engagement. It is the engine behind improved marketing results and creates measurable internal accountability as marketers become more effective in planning, executing, and proving the value of marketing.
- 192 - Def Data MiningData mining is the process of discovering interesting patterns and knowledge from large amounts of data.
(Alternative names: KDD, knowledge extraction, data archeology, information harvesting) - 202 - Formula Rescaling(x-min(x))/(max(x)-min(x)
- 213 - Def Machine LearningMachine learning is the „Field of study that gives computers the ability to learn without being explicitly programmed”
- 223 - types of learning(4)• Supervised learning(Fitting data to a function or function approximation)
• unsupervised learning(Figuring out what the data is without any feedback)
• semi-supervised learning(Training set with both labelled and unlabeled data)
• Reinforcement learning(Playing a game with rewards and payoffs) - 233 - Algorithms for un- & supervised learning
- 243 - def decision treeDecision Trees classify objects by their properties. They consist of a set of nodes and edges. Internal nodes contain characteristic attributes and Edges are labeled with attribute value conditions. The leaf nodes contain class assignment.
- 253 - Formula Information contentI(p1, ..., pn)=sum[i=1 to n](-pi * log2 (pi))
- 263 - Formula expected information contentE(X, T)=sum[i=1 to k](|Xi|/|X|*(I(pi, ..., pn))
- 273 - Formula Information GainG(X,T) = I(p1,..., pn) - E(X,T)
- 284 - Def SVMSVM are a set of related methods for supervised learning, applicable to both classification and regression
problems.
SVM classifiers create a maximum-margin hyperplane that lies in a transformed input space and splits the
example classes, while maximizing the distance to the nearest cleanly split examples. The parameters of the
solution hyperplane are derived from a quadratic programming optimization problem - 294 - Dif SVM-ANNSVM have simple geometrical interpretation and the training always finds a global
minimum - 304 - Applicatins of SVM• Text categorization
• Image classification
• Bioinformatics (Protein classification, Cancer classification)
• Hand-written character recognition - 315 - Advantes & Disadvantages of DT/ANN/SVM
Informações
- Descrição
- FlashCards sobre BIR, criado por Moritz Albrecht em 24-07-2017.
- Criado por
- Moritz Albrecht
- Visualizações
- 10
- Avaliação