%PDF-1.7
%
481 0 obj
<>/Metadata 513 0 R/Pages 478 0 R/StructTreeRoot 107 0 R/Type/Catalog/ViewerPreferences 499 0 R>>
endobj
513 0 obj
<>stream
Digital Marketing Analytics Personalization Attribution Measurement Machine Learning
Microsoft® Word 2016
Everyone has a marketing attribution problem, and all attribution measurement methods are wrong. We hear that all the time. Like all urban myths, they are founded on truth. Most organizations believe they can do better on attribution. They all perceive gaps, for example, missing touchpoint data, multiple identities across devices, arbitrary decisions on weightings for rules, and uncertainty on what actions to drive from results. Broadly speaking, the holy grail of media measurement is to analyze the impact and business value of all company-generated marketing interactions across the complex customer journey. Our goal is to take a transparent approach in discussing and demonstrating how SAS® is building data-driven marketing technology to help progress past typical attribution methods, and make the business case for customer journey optimization. Being SAS, we advocate an analytic approach to addressing the operational and process-related obstacles that we commonly hear from customers. We want to treat them as two sides of the same coin. The output of attribution analytics informs marketers about what touchpoints and sequence of activities drive conversion. This leads marketers to make strategic decisions about future investment levels, as well as more tactical decisions about what activities to run. In an ideal world, the results of subsequent actions are fed back into the attribution model to increase not only its explanatory power, but also its predictive abilities. <br/><br/>Suneel Grover, SAS <br/><br/>Malcolm Lightbody, SAS
Session 2111
en
jeff.foxx@sas.com
Everyone has a marketing attribution problem, and all attribution measurement methods are wrong. We hear that all the time. Like all urban myths, they are founded on truth. Most organizations believe they can do better on attribution. They all perceive gaps, for example, missing touchpoint data, multiple identities across devices, arbitrary decisions on weightings for rules, and uncertainty on what actions to drive from results. Broadly speaking, the holy grail of media measurement is to analyze the impact and business value of all company-generated marketing interactions across the complex customer journey. Our goal is to take a transparent approach in discussing and demonstrating how SAS® is building data-driven marketing technology to help progress past typical attribution methods, and make the business case for customer journey optimization. Being SAS, we advocate an analytic approach to addressing the operational and process-related obstacles that we commonly hear from customers. We want to treat them as two sides of the same coin. The output of attribution analytics informs marketers about what touchpoints and sequence of activities drive conversion. This leads marketers to make strategic decisions about future investment levels, as well as more tactical decisions about what activities to run. In an ideal world, the results of subsequent actions are fed back into the attribution model to increase not only its explanatory power, but also its predictive abilities. <br/><br/>Suneel Grover, SAS <br/><br/>Malcolm Lightbody, SAS
Microsoft® Word 2016
2018-04-02T16:02:31.000-04:00
2018-04-02T16:02:31.000-04:00
2018-03-08T20:17:34.000-05:00
2018-04-03T15:45:46.315-04:00
0ba9a88da345b2d1e30b8bf2e21356baaf06fcfb
639263
application/pdf
2018-04-03T15:45:46.237-04:00
Suneel Grover
Marketing Analytics Personalization Attribution
Algorithmic Marketing Attribution and Conversion Journey Analysis
uuid:40B596A9-9559-4801-9523-B1D77CB7D0B9
uuid:af45bcc6-05eb-4685-b20f-22bd158a36fa
thirdparty
support:sgf-papers
year:2018
cbo:130
support:sgf-papers/session-type/breakout
support:sgf-papers/topic/industry-specific-solutions
support:customer-roles/business-analyst
endstream
endobj
478 0 obj
<>
endobj
107 0 obj
<>
endobj
499 0 obj
<>
endobj
108 0 obj
<>
endobj
109 0 obj
<>
endobj
110 0 obj
[148 0 R 149 0 R 150 0 R 151 0 R 152 0 R 428 0 R 477 0 R 429 0 R 154 0 R 155 0 R 156 0 R 157 0 R]
endobj
111 0 obj
<>
endobj
112 0 obj
[427 0 R 426 0 R 159 0 R 160 0 R 425 0 R 424 0 R 162 0 R 163 0 R 164 0 R 165 0 R 166 0 R 167 0 R]
endobj
113 0 obj
[421 0 R 423 0 R 422 0 R 169 0 R 170 0 R 171 0 R 420 0 R 419 0 R 173 0 R 174 0 R 417 0 R 475 0 R 418 0 R]
endobj
114 0 obj
<>
endobj
115 0 obj
[416 0 R 415 0 R 177 0 R 178 0 R 413 0 R 473 0 R 414 0 R 180 0 R 412 0 R 411 0 R 182 0 R 183 0 R 184 0 R 185 0 R 186 0 R 187 0 R]
endobj
116 0 obj
<>
endobj
117 0 obj
[188 0 R 189 0 R 410 0 R 409 0 R 408 0 R 407 0 R 191 0 R 401 0 R 400 0 R 399 0 R 398 0 R 193 0 R 194 0 R 195 0 R]
endobj
118 0 obj
[392 0 R 391 0 R 197 0 R 198 0 R 390 0 R 389 0 R 200 0 R 201 0 R]
endobj
119 0 obj
[202 0 R 203 0 R 204 0 R 205 0 R 206 0 R 207 0 R 208 0 R 209 0 R 210 0 R 387 0 R 471 0 R 388 0 R 385 0 R 469 0 R 386 0 R 213 0 R 214 0 R 215 0 R]
endobj
120 0 obj
<>
endobj
121 0 obj
<>
endobj
122 0 obj
[384 0 R 383 0 R 217 0 R 218 0 R 219 0 R 382 0 R 381 0 R 221 0 R 222 0 R]
endobj
123 0 obj
[380 0 R 379 0 R 224 0 R 225 0 R 226 0 R 227 0 R 378 0 R 377 0 R 229 0 R 230 0 R 231 0 R 232 0 R 233 0 R]
endobj
124 0 obj
[376 0 R 375 0 R 235 0 R 236 0 R 237 0 R 374 0 R 373 0 R 239 0 R 240 0 R 241 0 R]
endobj
125 0 obj
[242 0 R 372 0 R 371 0 R 244 0 R 245 0 R 246 0 R 370 0 R 369 0 R 368 0 R 367 0 R 248 0 R 361 0 R 360 0 R 359 0 R]
endobj
126 0 obj
[354 0 R 353 0 R 251 0 R 252 0 R 253 0 R 254 0 R 352 0 R 351 0 R 256 0 R]
endobj
127 0 obj
[257 0 R 258 0 R 259 0 R 260 0 R 350 0 R 349 0 R 348 0 R 341 0 R 467 0 R 342 0 R 465 0 R 343 0 R 263 0 R 264 0 R 340 0 R 339 0 R 338 0 R 266 0 R 267 0 R 332 0 R 463 0 R 333 0 R 269 0 R 270 0 R 271 0 R]
endobj
128 0 obj
<>
endobj
129 0 obj
<>
endobj
130 0 obj
<>
endobj
131 0 obj
[272 0 R 330 0 R 461 0 R 331 0 R 328 0 R 459 0 R 329 0 R 326 0 R 457 0 R 327 0 R 324 0 R 455 0 R 325 0 R 322 0 R 453 0 R 323 0 R 320 0 R 450 0 R 321 0 R 318 0 R 448 0 R 319 0 R 316 0 R 446 0 R 317 0 R 281 0 R 314 0 R 444 0 R 315 0 R 283 0 R 284 0 R 285 0 R 286 0 R 287 0 R 309 0 R 441 0 R 310 0 R 307 0 R 439 0 R 308 0 R 290 0 R 291 0 R 292 0 R 293 0 R 294 0 R 305 0 R 437 0 R 306 0 R 303 0 R 435 0 R 304 0 R 297 0 R 430 0 R 433 0 R 431 0 R 298 0 R 299 0 R 300 0 R 301 0 R 302 0 R]
endobj
132 0 obj
<>
endobj
133 0 obj
<>
endobj
134 0 obj
<>
endobj
135 0 obj
<>
endobj
136 0 obj
<>
endobj
137 0 obj
<>
endobj
138 0 obj
<>
endobj
139 0 obj
<>
endobj
140 0 obj
<>
endobj
141 0 obj
<>
endobj
142 0 obj
<>
endobj
143 0 obj
<>
endobj
144 0 obj
<>
endobj
145 0 obj
<>
endobj
146 0 obj
<>
endobj
49 0 obj
<>/MediaBox[0 0 612 792]/Parent 478 0 R/Resources<>/Font<>/ProcSet[/PDF/Text]>>/Rotate 0/StructParents 21/Tabs/S/Type/Page>>
endobj
50 0 obj
<>stream
HWn~6 & ̌ AXv (T,Ź%v,X:u/^˻{=|y}۷n|y}}
/|vqY/o_tSw(;\{ wNKM[wǹcwO JpX0\M?A|?C!:.E͙7FNǰeJ&:-~ϰ2"Q~D/_t#F>|*itCBǂʭ8J98]\2RveDT!`)=3@$̃2.o'DRp!sS+zǤZhbpAr֗p
17M\Ħyx'r~}d dū{WzX+`ux/IKNt__;"b&H#_m=[U::l,dI۸ ~-C|ۑܒ&m"F~fܶUX4|)W.OBސZvL}/ 8;
8gbEt
A!5T*.|YY}0@B0e*8ѐo|N*A^L/I|PaPJM]Z\)8A *l#X Z)z]mO"3͖ENDB#<Њt:I4x"]HWs4~pOY֓JZ?gqѽ`v{=P`qp݉Zba dS?[PW796uRuI9( ِ(dR"lxzId0+AJ[sH:BRo8֧skjD99.OD*):