a
- academic institutions, 322–323
- accuracy, 25, 37, 84, 141, 190, 215, 236, 252, 295, 296, 301
- activity-based costs, 53
- ad-hoc reporting, 10
- advertising, 13, 15
- Aerospike, 97
- AIC, 247
- algorithmic evaluation, 235
- algorithmic modeling, 231, 236
- data acquisition, and cleaning, 236–237
- feature engineering, 237–238
- model fitting (training) and feature selection, 240–241
- model implementation, 242
- modeling overview, 238–239
- model performance assessment, 242
- model (algorithm) selection, 241–242
- alternate solution methods, 200–206
- Analysis of Variance (ANOVA), 124–126
- analysis/query/drill-down, 10
- analytical
- capability,
- ecosystem, building, 73–74
- groups, goals of, 62
- life cycles, 63
- organization, 74
- practice, 52
- practitioners,
- professionals, 57
- skills, 56
- specificity, 39
- talent, 57
- analytics applications, 313, 317, 320, 322, 324
- Analytics 1.0, 32
- Analytics 2.0, 32, 37
- Analytics 3.0, 32
- analytics-based system, 45
- analytics categories,
- descriptive, –10
- data modeling,
- reporting, 10
- software, 10
- visualization, 10
- predictive, 10–14
- data mining, 11
- forecasting, 11
- leveraging expertise, 12–14
- pattern recognition, 11
- predictive modeling, 11
- simulation, 11
- prescriptive analytics, 14–16
- Analytics Certification Board, 50
- analytics-focused software developers, 317–319
- predictive analytics, 318
- prescriptive analytics, 318–319
- reporting/descriptive analytics, 317–318
- analytics industry analysts, and influencers, 321–322
- analytics industry ecosystem, 312–325
- business analytics professionals, 312
- communicator, 312
- mathematicians, 312
- modeler, 312
- programmer, 312
- analytics initiative, 49
- analytics methodology, for life cycle management, 276–303
- business understanding, 276, 278
- data preparation, 276, 288–289
- data understanding, 276, 288–289
- deployment, 276, 297–300
- evaluation, 276, 294–297
- modeling, 276, 293–294
- analytics model, deployment, 298–300
- analytics practitioner
- macro-solution methodologies, 106
- analytics problem framing, 278, 283–287
- analytics problem statement, 284, 286–289, 292–293, 295
- analytics process, , 78
- analytics professional (AP), , 24, 275–284, 286–288, 291, 293–296, 298–300, 303–309
- analytics project, 17, 142
- desired outcome, 145
- documentation, 148
- finding the right answer, 148–149
- lack of perceived success, 148–149
- life cycle, 293
- null hypothesis, 146
- OR field, 145
- real-world, 101
- research-and-discovery-leaning, 109
- software and tool selection, 142–143
- systematic solution methodologies, 145
- analytics solution, determine, problem amenable, 281
- analytics space, 314
- analytics/technical skills, 57
- analytics to detect new fraudulent claims, 45
- analytics user organizations, 323–325
- analytics within organizations, 16
- communicating analytics, 21–
- organizational capability, 21–23
- projects, 17–19
- analytic teams,
- analyzing data,
- annual performance assessments, 58
- ANOVA, 104, 124, 125
- anti-discrimination laws, 24
- AP. See analytics professional (AP)
- application developers, industry-specific/general, 319–321
- analytics software providers, 319
- data aggregators, 319
- data infrastructure, 319
- data warehouse, 319
- middleware, 319
- ARENA, 319
- Aristotle, 106
- ARMA methods, 138, 140
- ARPANET configuration, 136
- artificial intelligence (AI) systems, , 52, 56, 231, 234
- Asset ID, 93
- assigned customers, 67
- Associate CAP (aCAP), 49
- audio, 39
- auditability, 25
- audit cycle, 82
- automated control protocol, 156
- automated data collection, 82
- automation, 85
- automobile insurance, 45
- automotive manufacturers, 15
b
- backpropagation, 264
- Bacon, Francis, 106
- bad data, 39
- balancing bias, 245–247
- bank’s branch network, 53
- Baker, S., 322
- BIC, 247
- bias-variance trade-off, 243
- big data, , , , , 33, 52, 59, 74, 95, 120, 121
- binary/binomial classification, 233
- binning, 89, 90
- box-and-one approach to teaching with cases, 343–344
- black box, 11
- breadth, 39
- Brown, G., 214
- bureaucracy, 62
- business, 66
- acumen, 50, 52, 60
- analytics professionals, 312
- benefits, 281–282
- customers, 69
- intelligence, 50, 54
- leaders, 57, 58, 69
- models, 295
- operations,
- opportunities, 320
- performance, 295, 308
- problem framing, 278
- problem statement, 278–279, 281, 283, 285, 287–288
- relationship, 305
- structure, 69
- understanding, 278, 297
- value, 50, 54
- business knowledge, 50
- business-oriented translators, 51
c
- C, 207
- C++, 95
- call centers, 74
- CAP Certification. See Certified Analytics Professional certification
- CAP Job Task Analysis (JTA), 277
- case study
- alternate solution methods, 200–206
- portfolio optimization, solved by a variety of methods, 178–181
- traveling salesman problem, 200–206
- Cassandra, 97
- centralization, 61, 62
- centralized analytics groups, 62, 69
- CEP. See complex event processing
- certification agencies, 322–323
- certification programs, 49, 322
- Certified Analytics Professional (CAP) certification, 49, 58, 277, 299, 301, 323
- changing world of analytics, 25–28
- Chief Analytics Officers (CAO), 23, 70
- Chief Data Officer, 70
- Chief Data Scientists, 70
- Chief Executive Officer, 324
- Chief Information Officer, 324
- citizen data scientist, 311
- Clark, Robert, 96, 312
- classification problems, 232, 233
- cleaning data, 28
- cleansing, 36
- C-level positions,
- client, 160
- cloud computing, 315
- cluster documents, 234
- clustering methods, 233
- coaching, 51
- Codd, E.F., 93
- cognitive
- burden, 10
- computing,
- technologies, 52
- Cognos software, 10
- cohesion, 58
- COIN-OR, 143
- collaboration, 35, 41
- collecting data,
- columnar databases, 96
- combinations, 162
- commercial analytics group, 74
- communicating analytics, 21
- communication, 10, 303, 305–306
- device, 44
- model-advised thumb rules, 226–227
- model obsolescence, 226–227
- model solutions, 224–226
- monotonicity, 223–224
- persistence, 223–224
- quality, 305
- report writers, 221–222
- skills, 60, 281, 283, 300
- with stakeholders, 220
- standard form model statement, 222–223
- strategies for improvement, 305–306
- training for model, 221
- verbal communications, 286, 306
- written communication, 286, 306
- communities, , 62, 67
- competition, 15
- competitive advantages, 32
- complex event processing (CEP), 319
- complex queueing system, 130
- computational infrastructure, 39
- computational power,
- computer
- conceptual framework,
- conditional probability, 163
- conduct data-driven experiments, 54
- confidentiality, 38
- confusion matrix (truth table), 249, 250, 252
- consulting firms, 32
- consulting skills, 51
- contextual knowledge,
- continuous data, 79
- coordination approaches, 65–66
- coordination mechanisms, 66–67, 70
- corporate litigation, 56
- correction, 36
- cosine similarity, 272
- cost,
- cost-effective, 37
- credibility, 14, 53
- credit score, 320
- CRISP-DM. See cross-industry standard process for data mining
- critical path method (CPM), 142, 176–178
- Gantt chart (deterministic, descriptive), 177
- cross-channel analytics, 74
- cross-channel perspective, 74
- cross-functional team,
- cross-industry standard process for data mining (CRISP-DM), 112, 276
- CRISP-DM diagram, 277
- CRISP-DM methodology, 278
- CRISP-DM Phase 1, 278
- CRISP-DM Phase 2 and 3, 288–289
- CRISP-DM Phase 4, 293–294
- CRISP-DM Phase 5, 294–297
- CRISP-DM Phase 6, 297–298
- methodology, 106, 112–113, 137, 140
- business understanding, 112–113
- data preparation, 113
- data understanding, 113
- deployment, 113
- evaluation, 113
- modeling, 113
- OR project method, 113
- steps of, 112
- cross-sectional data, 79
- CRUD cycle, 98
- customer data integration (CDI), 98
d
- Dantzig, G., 181
- data
- about data, 98
- access to, 40
- acquisition, and cleaning, 236, 290–291
- analysis,
- analytics, 311–312
- captured, 38, 98
- cleaning, 17
- collecting and applying analytics business, 45
- collection, 42, 77, 108, 109, 314
- culture, 42
- discovery, 80–86, 81
- driven decisions, 49
- elements,
- exhaust,
- exploration, , 10
- extrapolation, 217–218
- generation, 314
- infrastructure providers, 314–315
- governance, 38
- harmonization, rescaling, cleaning, and sharing, 291–292
- integrity, 217
- interpolation, 217–218
- literate, 55
- management, 50, 52, 97–98
- infrastructure providers, 315
- big data space, 315
- cloud computing, 315
- SQL server, 315
- oriented employees, 57
- skills, 50
- master, 98
- mining, 51
- modeling, , 93
- nonrelational databases, 95–97
- relational databases, 93–95
- need and sources, identifying and prioritizing, 290
- numeric, 55
- old, 45
- potential sources,
- process, 38
- products, 52
- profiling, 86, 87
- quality control, 39
- quantity, 37
- reduction, 92
- relationship identification, 292–293
- reporting, 10
- resources,
- rules, for usage (See rules, for data usage)
- science, , , 59, 61
- scientists, 36, 38, 52, 54, 61, 62, 63
- security, 59, 323
- semistructured, 37
- sensor, 43
- service providers, 316–317
- sets
- variability in size and information density,
- small, 27
- squashing, 93
- stewards, 98
- storage, 84
- structure, 37, 291–292
- thick,
- transmission errors, 121
- “typical” sets, 41
- useful, 37
- visualization, 10, 55, 317
- warehouse providers, 316
- database
- computing, 315
- key-value pair, 37, 97
- data-centric approach, , , ,
- data-centric groups,
- data preparation, 86–93
- data types, 77
- binary data, 78
- continuous data, 79
- cross-sectional data, 79
- nominal data, 77
- ordinal data, 78
- panel data, 79
- qualitative data, 77
- quantitative data, 79
- spatial data, 79
- time series data, 79
- unstructured text data, 80
- data understanding phases, 303
- Davenport, T., 322
- Davenport identifies Analytics 1.0, 2.0, and 3.0, 31
- decentralization, 62, 63
- approach, 63
- direction, 62
- decimal scaling, 91
- decision-centric analytics,
- decision-centric approaches, , ,
- decision-centric framing,
- decision-centric organizations,
- decision-makers, , 15, 53
- Decision theory, 184–187
- decisions, , 37
- better,
- levers, 15
- making rules, 50
- making space, 235
- process, 41
- theory, 184–187
- tree, 129
- variables, 132
- deep learning, 27, 52
- deliver project model, 299
- demand vs. nonfill percentage, 123
- density methods, 233
- deployment
- descriptive analytics, 10, 52
- descriptive–predictive–prescriptive analytics paradigm, 105
- deterministic models, 161–162
- developing talent, 58–59
- digital food pantry, 122
- digital simulation, 173–174
- coin toss simulation (stochastic, descriptive), 173
- static vs. dynamic simulations, 174
- dimension reduction, 233
- disciplines, , 50, 105, 106, 312
- scientific, 106
- using analytics in research and practice, 144
- discrete data, 79
- discrete event simulation, 130
- disease class, 233
- distance education, 59
- DIY software, 142
- documentation, 39, 116, 142, 148, 166, 170, 206, 216, 290, 297, 303–305
- document-oriented database, 97
- domain
- Drucker, P., 215
- dual solution, 183
- Duhigg, C., 322
- dynamic programming, 195–196
e
- Eckerson, W., 322
- economic order quantity (EOQ), 162, 174
- economic variables, 15
- ecosystem exchange information, 314
- education level, 24
- effective data management programs, 98
- Einstein, A., 208, 228
- electric utilities, 85
- electronic medical records (EMR), 319
- e-mail, 38
- e-mail addresses, 89
- EMR. See electronic medical records
- engineering, 15
- Enterprise Data, 59
- Enterprise Miner, 318
- ethical implications, 23–25
- ethics, 25, 26
- execution performance, 40
- executive sponsor, 35
- executives, 57, 160
- experimentation skills, 52
- explainability, 25
- extract, transform, and load (ETL) procedures, 81
f
- Facebook, 44, 73, 320, 321
- fairness, 25
- fat fingering, 83
- FCC. See Federal Communications Commission
- Federal Communications Commission (FCC), 323
- Federal Trade Commission (FTC), 323
- federation, 67
- feedback loop, 296
- finance, 50, 73, 320
- fitbit health record, 23
- five tasks, importance of, 33
- assemble the team, 34–36
- execute, 42
- prepare the data, 36–39
- selecting analytics tools, 39–41
- selecting the target problem, 33–34, 33–36
- five “V’s,” 36
- foodservice data provider, 45
- foriegn key, 93
- Fortran, 207
- Franks, B., 322
- fraudulent claims, 45
- FTC. See Federal Trade Commission
- function system, 156
- funding sources, 69
g
- game theory, 15, 181–184
- generic data models,
- Gladwell, M., 322
- Go Grandmaster, 235
- Google, 55, 73, 314, 315, 317, 321
- Google Earth, 221, 228
- Google Maps, 158
- Google’s recruiters, 55
- government agencies, 309
- Government Performance and Results Act, 309
- granular (disaggregated) data, 38
- granularity, 38, 45
- graph-based models, 138
- graph database, 37, 97
- Gross Domestic Product (GDP), 14
- Guidelines on ethics, INFORMS, 26
h
- hackers, 23
- Hamming, R., 227
- hardware, 54
- Harris, Jeanne, 55, 62, 64
- high-demand resource, 61
- high-quality analytical work, 49
- high-velocity analytics, 43, 44
- for quick response to customers, 44
- to save maintenance costs, 44–45
- to save operating costs, 43–44
- Hughes’ Salvo Model of Combat, 192–193
- human analytical resources, 49
- human decision-making, 53
- human resources (HR), 59
- leadership, 59
- organizations, 59
i
- IBM, 112
- IBM ILOG CPLEX toolbox, 143
- IBM-SPSS Modeler, 318
- ICT. See information and communication technologies
- IDC. See International Data Corporation
- image analytics, 39
- Imhoff, C., 322
- industrial engineering,
- inferential statistics, 169–170
- information, 58
- information and communication technologies (ICT), 323
- information management system, 43
- information technology, , 72, 312
- expert, 35
- management, 275
- organizations, 72
- professionals, 56, 299
- team, 44
- InfoPlus.21 data historian, 85
- INFORMS. See Institute for Operations Research and the Management Sciences
- INFORMS conference, 103, 105, 111–112
- infrastructure funding, 70
- INFORMS Transactions on Education (ITE), 332–333, 337
- Inman, B., 322
- innovation, 54, 70, 131
- innovative data-based products, 54
- Institute for Operations Research and the Management Sciences (INFORMS). 26, 49, 58, 103, 105, 111–112, 228, 332
- insurance, 71, 184
- health insurance industry, 319
- intelligent hypotheses, 55
- Interfaces, 228
- internal consulting company, 23
- International Data Corporation (IDC), 311
- International Telecommunication Union (ITU), 323
- Internet, 23, 156
- Internet of Things (IoT), 25, 85, 315
- Internet Protocol models, 207
- interpersonal attributes, 53
- interpret data, 54
- interview
- with Camm, Jeffrey D., 160
- with Clark, Robert, 96, 312
- with Cochran, James J., 214–215
- with Loh, Wei-Yin, 259
- with Roberts, Greta, 34, 56
- with Scheinberg, Katya, 264–265
- with Schramm, Harrison, 43, 80
- with Smith, Cole, 209–210
- with Stephens, Eric, 19–20, 102–103, 325–326
- with Taber, Alan, –, 146–147, 280
- with Walker, Russell, 60–61, 306–307
- Introduction, Methods, Results, and Discussion (IMRAD), 108
- invent and pilot stage, 17
- inventory management systems, 314
- IoT. See Internet of Things (IoT)
- irreducible error, 244
- irrevocable allocation of resources,
- ITE, See INFORMS Transactions on Education
- ITU. See International Telecommunication Union
j
- Jaccard Index, 271
- Java, 95
- Java Script Object Notation (JSON), 97
- job task analysis (JTA), 277
- JTA domain I task 1, 278–283
- JTA domain I task 2, 279–280
- JTA domain I task 3, 281
- JTA domain I task 4, 281
- JTA domain I task 5, 281–282
- JTA domain I task 6, 282–283
- JTA Domain II, Task 1, 283–285
- JTA Domain II, Task 2, 285–286
- JTA Domain II, Task 3, 286
- JTA Domain II, Task 4, 287
- JTA Domain II, Task 5, 287–288
- JTA Domain III, Task 1, 290
- JTA Domain III, Task 2, 290–291
- JTA Domain III, Task 3, 291–292
- JTA Domain III, Task 4, 292–293
- JTA Domain III, Task 5, 293
- JTA Domain III, Task 6, 293
- JTA. See job task analysis (JTA)
k
- Karush–Kuhn–Tucker (KKT), 133
- KDNuggets, 276
- key performance indications (KPIs), 308
- key-value relationship, 97
- key-value store, 97
- k-fold cross-validation, 246
- KNIME, 318
- knowledge, , , 13, 22, 34, 36, 90, 108, 113, 146, 237, 279
- Knuth, D., 218
- KPIs. See key performance indications
- KXEN, 318
l
- Lanchester models of warfare, 189–192
- Warfare, Lanchester Models, 189–192
- aimed fire square law, 190
- area fire linear law, 190–191
- simulation, 191–192
- Lanchester, F.W., 189
- Lanchester's Square Law, 191–192
- language system operator’s, 160
- leadership, 62
- Lean Six Sigma certifications, 325
- life cycle management, 275–276, 303–309
- life cycle of analytics projects, 18
- linearized feasible region, 134
- linear programming (LP), 133
- classification models, 138, 139
- clustering models, 138, 139
- generalized linear models, 138
- graph-based models, 138, 140
- LinkedIn, 320
- Loess Regression, 91
- Loh, Wei-Yin, 259
m
- machine age,
- machine learning, , 11, 27, 57, 231, 232, 234, 235
- goals and guiding principles in, 235–236
- practitioners, 231
- macro-methodology. See macro-solution methodologies
- macro-solution, 103
- macro-solution methodologies, 103, 106, 144, 146
- analytics project, 114–116
- cross-industry standard process for data mining (CRISP-DM) methodology, 112–113
- operations research project methodology, 109–112
- relationship, 115
- scientific method, 145
- scientific research methodology, 106–109
- software engineering-related solution methodologies, 114
- take-home message, 116
- make to order (MTO), 85
- make to stock (MTS), 85
- management process, 17
- management science/operations research (MS/OR) software, 318
- management skills, 51
- managers, 51
- manufacturing, 15
- marketing, 15, 32, 36, 50, 64, 69, 73, 304, 321, 322
- market research,
- master data, 98
- master data management (MDM), 98
- mathematical method,
- mathematical model, 158
- mathematical optimization, 127, 174–175
- economic order quantity, 175
- mathematical programming techniques, 131–133
- discrete, combinatorial, and network optimization, 135
- integer programming, 135
- linear programming (LP), 133
- mixed integer programming, 135
- nonlinear programming (NLP), 133
- mathematicians, 312
- mathematics,
- MATLAB, 143, 318
- matrix, 67–69, 92, 172, 181, 183, 184, 195, 249
- McDonald, Bob, 54
- mean squared error (MSE), 248
- mean absolute deviation (MAD, aka mean absolute error (MAE), 248
- measurement units, 175–176
- units in expressions, 176
- medical images, 39
- metadata, 98
- methodology
- metrics, 308–309
- creation and usage, 301–303
- Government Performance and Results Act 1993, 309
- micro-methodology. See micro-solution methodologies
- Microsoft EXCEL, 143
- micro-solution methodologies, 103, 141, 144
- description framework, 117–118
- for exploration and discovery, 119–126
- preliminaries, 116–117
- pseudo- or quasi- forms, 135
- techniques to find solutions
- middle managers, 54
- middleware providers, 316
- min–max, 91
- missing at random (MAR), 88
- Minitab, 143
- missing completely at random (MCAR), 88
- missing values, 39, 87
- mixed-integer programming, 318
- model, 155, 159
- counting, 162
- deterministic/stochastic, 161–162
- development, 235
- documentation (See model documentation)
- error, 243
- exponential, poisson, and memoryless, 171
- failure, objective criteria, 160
- fitting, 243, 245–247
- in business, 68
- home location, 68
- work location, 68
- formulation, 206–207
- goals shifting, 160
- map, 156
- mathematical, 158
- obsolescence, 226–227
- physical, 157
- prescriptive, 15
- problem and improtance/solution, 159–160
- queueing, 170
- solutions, 224–226
- success
- technique, 159–160
- time series, 138
- types of, 161
- descriptive, 161
- predictive, 161
- prescriptive, 161
- validation, 218–220
- verification, 218–220
- comparing models, 218–219
- data diagnostics, 220
- data provenance, 220
- data vintage, 220
- sample data, 220
- model documentation, 206
- with different methods, 211–212
- with different variables, 212–213
- extensibility, 214–215
- formulation, 206–207
- implementation language, choice of, 207
- model fidelity, 208–210
- reliability, 213
- scalability, 213
- sensitivity analysis, 210–211
- stability, 213
- supervised vs. automated models, 207–208
- modeler, 24, 159, 312, 318
- Modeling General Motors, 15
- MongoDB, 97
- Monte Carlo simulation, 15, 54, 130
- Morison, Bob, 62, 64
- MS/OR. See management science/operations research
- multiclass/multinomial classification problems, 233
- multi-variate analysis of variance (MANOVA), 104, 124, 126
- Murray, Desmond, 59
n
- National institute of Standards and Technology (NIST), 323
- natural gas, 85
- network models, 127
- neural networks, 138, 140
- deep learning, 264
- recurrent neural networks, 264
- software, 318
- new data, 10, 38, 39, 45, 235, 237, 260
- new technical skills, 52
- Newton's second law, 161
- NIST. See National institute of Standards and Technology (NIST)
- nominal data, 77
- nondeterministic polynomial (NP) time, 133
- nonlinear programming (NLP), 133
- nonrelational database technologies, 80
- nonstandard values, 88
- normalization, 91
- North American Automobile Market, 15
- NoSQL database, 95
- not missing at random (NMAR), 87
- number in line, 131
o
- obtain/receive problem statement and usability, 278–279
- obtain stakeholder agreement on business statement, 282–283
- Ohm’s law, 219–220
- Oklahoma State University, 324
- old and new data plus analytics
- online channels, 74
- online social media, 320
- operational analytics, 52
- operational data store (ODS), 81
- operations data, 44
- operations research,
- operations research project methodology, 106
- optimization, , 15, 39, 81, 104, 110, 127
- ordinal data, 78
- organization, 16, 23, 49, 53, 57, 58, 62, 63
- capability, 21–23
- commitment, 61
- decision-making,
- designs, variables for tuning, 68
- IT functions,
- requirements for analytical capabilities, 49
- structures, 70, 293
- organizing analytics, basic models for, 63
- center of excellence model, 65
- centralized model, 63
- consulting model, 64
- decentralized model, 65
- functional or “best home” model, 64
- ORION, 52
- OR/MS textbook, 109
- OR/MS Today, 228, 319
- OR project methodology, 110, 111, 112
- ORSA/TIMS conference, 132
- overfit, 243
p
- panel data (or longitudinal data or cross-sectional time series data), 79–80
- payoff matrix, 181, 184
- peer review, 100, 108
- permutations, 162
- pervasive data, ,
- physical model, 157
- PI data historian, 85
- planners, 160
- point of sale (POS) systems, 85
- portfolio optimization
- assessing our progress, 179
- heuristic, 179
- relaxations and bounds, 179–180
- simple optimization problem, 180
- post-deployment activities, 301–303
- powerful computation,
- predictive analytics, 57, 58
- predictive performance evaluation, 247–248
- classification performance, 249–253
- performance evaluation for time-dependent data, 253–254
- regression performance, 248–249
- prescriptive analytics, 15, 57
- price,
- primary key, 93
- principal components analysis (PCA), 92, 234, 270
- principle of optimality, 195–196
- privacy, 23, 33, 38, 281, 290, 321, 323
- private sector organizations, 309
- probability, 163
- Bayes theorem, 163–164
- binomial model of coin tosses, 164
- independence assumption, 163
- models, 127
- multiplication rule, 163
- perspectives and subject matter experts, 165
- synonyms for, 164
- probability models, 127
- problem
- problem-solving, 99, 100, 102
- research on operations, 137
- visualization, 143–144
- product design-to-market cycles, 32
- product development, 52, 73
- product information management (PIM) tools, 98
- productionization, 17
- professional analysts, 54
- professional communities,
- profitability, 15, 16, 22, 53
- program evaluation and review technique (PERT), 142
- Program Management Office (PMO), 65, 66, 67
- programmers, 51
- projects, 17–20
- based funding, 69
- manager, 35
- planning, 142
- public sector organizations, 295
- purchasing decision, 41
- Pyomo, 207
- Pyramid of Analytic Knowledge, 60
- Python, 143, 207, 228
q
- qualitative data, 77–79
- quality, 38
- quantitative analysts, 50
- quantitative analytics professionals, 17
- quantitative data, 79–80
- quantitative methods, 105
- quantitative skills, 50
- queueing models, 127
- query, 94
- queueing theory, 128
r
- R, 207, 318
- RapidMiner, 318
- rationalization, 70
- real goal, 42
- real-life, 15
- real-time traffic information, 320
- real-time transaction data, 27
- Receiver operating characteristics (ROC) curves, 250–251
- recidivism models, 24
- refine problem statement, and delineate constraints, 281
- regularization, 247
- regression, linear least-squared error, 167–169
- regression model error, components of, 243–245
- regression problems, 232
- regulators, and policy makers, 323
- Federal Trade Commission (FTC), 323
- information and communication technologies (ICT), 323
- International Data Corporation (IDC), 311
- International Telecommunication Union (ITU), 323
- National Institute of Standards and Technology (NIST), 323
- reinforcement learning, 233, 234
- relational database, 37, 93–95
- relational database management system (RDBMS), 93
- relationship skills, 51
- reporting, 10
- resource utilization, 131
- response functions, 233
- responsibility, 17, 24, 25, 75, 276, 298–300
- revolution analytics, 318
- risk management, 62
- Roberts, Greta, 56–57
- rolling-horizons design, 253–254
- root mean squared error (RMSE), 248
- Rose, Robert,
- rotation, 67
- R package, 143
- “R-squared” metric, 12
- rules, for data usage
- copyright, 216
- data integrity, 217
- Department of Defense, 216
- Department of Energy, 216
- Institutional Review Board (IRB), 216
- law enforcement data, 216
- licensed data, 215–216
- model outputs, displays of, 217
- multiple data evolutions, 217
- paraphrased and plagiarized data, 217
- personally identifiable information (PII), 216
- proprietary data, 215
- Protected Critical Infrastructure Information System (PCIIMS), 216
- trademark, 216
s
- sale systems, 314
- Salford Systems, 318
- SAP system, 110, 316
- SAS, 112, 113, 143, 276, 316, 317, 318, 319, 322
- saving operating costs, 43
- Scheinberg, Katya, 264
- Schramm, Harrison, 43, 80
- scientific experimental design, 55
- scientific method. See scientific research methodology
- scientific research methodology, 106–109
- scoring function, 234
- search theory, 189
- area search (stochastic, predictive), 189
- security, 17, 19, 23, 25, 35, 38, 89, 95, 98, 268, 290, 313, 320
- segment-by-segment decisions, 15
- semistructured data, 37, 97
- semisupervised learning, 232
- SEMMA (Sample, Explore, Modify, Model, and Assess), 276
- senior management team, 54
- sensitivity (recall, true positive rate (TPR), or detection probability) vs. specificity (true negative rate), 250
- sensor data, 43, 44
- sentencing decisions, 24
- shared services, 72–73
- sharing, 41
- shelf life, 37
- SIGDSA. See Special Interest Group on Decision Support and Analytics (SIGDSA)
- Silicon Valley, 52
- simple random sample (SRS), 92
- simple random sampling without replacement (SRSWOR), 92
- simple random sampling with replacement (SRSWR), 92
- simplex method, 132
- simulation, , 11, 15, 55, 81, 82, 111, 127
- single-use models, 193–195
- compound interest and net present value, 193
- cost to maintain safety stock, 194–195
- skewness, 90
- skills, 50, 55, 57
- small data, , 27
- smart humans, 53
- smart machines, 53
- smartphones, 320
- social media, 44, 80
- data, 38
- driven content, 95
- social network analysis, 320
- social security numbers, 89
- softer questions,
- software, 10, 41, 54, 57, 227–228
- engineering methodology, 106
- selection
- skill, 50
- tools, 227
- software engineering-related solution methodologies, 114
- design, 114
- implementation, 114
- maintenance, 114
- requirements, 114
- verification, 114
- solution methodologies
- analytics breakdown, 104
- defined, 99, 100
- implementation, 102
- macro/microlevel analytics, 103
- vs. products, 101–103
- sophistication, , 39
- spatial data, 79
- Special Interest Group on Decision Support and Analytics (SIGDSA), 322
- sports analytics, 319
- Spotfire software, 10
- SPSS, 112, 113, 143, 276
- SQL Server BI tool kit, 317
- stack-based enumeration, 197
- combinations, 199–200
- data structures, 197–198
- generating permutations and combinations, 199–200
- Stackelberg game, 182
- staff development skills, 51
- stakeholder agreement, obtainment, 287–288
- stakeholders, 36, 42
- standardization, 36
- standard reporting, and dashboards, 10
- standard systems design, 299
- Starbucks network, 44
- statistical learning, 231
- “statistically significant” effect, 11
- statistics, , 53
- analysis of data, 166
- descriptive statistics, 166
- inferential, 169–170
- method,
- models, 50
- parameter estimation with confidence interval, 166–167
- random sample, 166
- regression, 167–169, 233
- Statsoft, 318
- Stephens, Eric, 19–20, 325–326
- stochastic gradient descent, 240
- stochastic models, 127, 161–162
- stochastic process, 128, 170–173
- exponential, poisson, and memoryless models, 171
- Markov chains (stochastic, descriptive), 171–172
- M/M/1 queue (stochastic, descriptive), 172–173
- queueing model, 170–171
- stock keeping units (SKUs)
- pairwise correlation coefficient, 123
- stored procedures, 95
- stress testing, 308
- string testing, 308
- structured data, 37, 38
- structured formats, 63
- structured query language (SQL), 93
- subject matter expert/expertise (SME), , , 15, 17, 81, 161, 165–166
- sum of squared errors (SSE), 247
- supervised learning algorithms, 254
- artificial neural networks, 262–264
- classification and regression trees, (CART), 257–259
- ensemble methods, 265–267
- extensions to regression, 256–257
- KNN (k-Nearest Neighbors) algorithm, 255–256
- overview, 254–255
- support vector machines, (SVM), 261–262
- time series forecasting, 259–261
- supervised learning methods, 235
- selection, and deployment, 235
- supervised learning problems, 232
- Supervisory Control and Data Acquisition (SCADA), 84
- supply chain software, 101
- susceptible, exposed, infected, recovered (SEIR) epidemiology, 187–189
- deterministic/predictive, 188
- system, 155
- dynamics simulation model, 15
- function, 156
- operators, 156, 159
t
- Taber, Alan, , 280
- Tableau software, 10, 316, 317, 322
- talent map, 57
- team budget, 41
- technical factors, 39
- selecting analytic tools, 39
- technical skill, 50
- telecommunications industries, 55
- teleprompter, 11
- temporal alignment, 39
- Teradata, 276, 315, 316, 319, 322
- testing, 307–308
- text data, 80
- thick data, ,
- time flow mechanism, 130
- time series data, 79
- time series models, 138, 140, 259–260
- tool selection, analytics project, 142–143
- trade-off, 37
- traditional quantitative analysts, 63
- traditional statistical methods, 27
- training program, 58
- transaction-oriented systems, 83
- transformation, 36, 54
- Transmission Control Protocol (TCP), 207
- traveling salesman problem, (TSP), 200–206
- trucking company, 43
- trusting relationship, 53
- type I errors (false positive errors), 169, 170, 196, 250
- type II errors (false negative errors), 169, 170, 196, 250
- Twitter, 44, 320
u
- underfit, 243
- units in expressions, 176
- unstructured data, 37, 38, 39, 52
- unsupervised learning algorithms, 267
- association rule mining, 268–269
- bag-of-words and vector space models, 271–272
- clustering methods, 269–270
- kernel density estimation, 267–268
- principal components analysis (PCA), 270–271
- unsupervised learning method, 233, 234
- unsupervised learning problems, 232
v
- validation, 11, 12, 18, 36, 110, 111, 131, 218, 238, 239, 242, 246, 253
- valuable information, 15
- value, 15, 22, 33, 36, 50, 64, 79, 86, 88, 89, 91, 97, 179, 184, 201, 217, 241, 249, 261, 263, 303, 314
- variable completeness, 38
- variance, 245–247
- variety, 36
- vehicle marketplaces, 15
- velocity, 36, 37
- vendors, 41
- veracity, 36, 37
- video, 39
- virtual reality (VR), 321
- visual analytics, 50, 52, 317
- Visual Basic for Applications (VBA), 207
- visual displays, 52
- visual format, 57
- visualization, 42
- capability, 40
- histograms, boxplots, scatter plots, and heatmaps, 121
- problem-solving, 143–144
- requirements, 39
- voice recognition tools, 320
- volume, , 15, 27, 36, 45
- VR. See virtual reality (VR)
w
- waiting time, 131
- Walker, Russell, 60, 306–307
- warehouse, 10
- web browsing data, 27
- Web sites, 80
- Weka, 318
- Western capitalist culture, 102
- Wide-Column stores, 37
- Woolsey, G., 224
- work ethic, 305
- work orders table, 93
- World Wide Web, 31
x
- XML, 97
- XPRESS toolbox, 143
..................Content has been hidden....................
You can't read the all page of ebook, please click
here login for view all page.