Meta-Learning Enhanced Trade Forecasting: A Neural Framework Leveraging Efficient Multicommodity STL Decomposition

<table class="table-group" id="tab5"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left">Model</td><td class="align_center">MAE <svg height="13.8595pt" id="M167" style="vertical-align:-2.2681pt" version="1.1" viewbox="-0.0498162 -11.5914 34.2622 13.8595" width="34.2622pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M300 -147C201 -63 143 98 143 270S200 602 300 686L282 710C136 610 70 450 70 271V270C70 89 136 -72 282 -170L300 -147Z"></path></g><g transform="matrix(.013,0,0,-0.013,4.498,0)"><path d="M528 54L331 254L528 455L492 493L294 291L96 493L60 455L257 254L60 54L96 16L294 217L492 16L528 54Z"></path></g><g transform="matrix(.013,0,0,-0.013,12.129,0)"><path d="M384 0V27C293 34 287 42 287 114V635C232 613 172 594 109 583V559L157 557C201 555 205 550 205 499V114C205 42 199 34 109 27V0H384Z"></path></g><g transform="matrix(.013,0,0,-0.013,18.369,0)"><path d="M241 635C89 635 35 457 35 312C35 153 89 -12 240 -12C390 -12 443 166 443 312C443 466 390 635 241 635ZM238 602C329 602 354 454 354 312C354 172 330 22 240 22C152 22 124 173 124 313S148 602 238 602Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,24.656,-5.741)"><path d="M247 635C116 635 39 518 39 421C39 315 113 237 221 237C239 237 258 241 281 253L349 289C315 140 204 42 60 19L66 -15C90 -15 153 -5 207 16C344 70 447 199 447 385C447 521 373 635 247 635ZM231 598C329 598 356 478 356 390C356 371 355 347 352 325C330 309 297 297 262 297C179 297 127 369 127 456C127 515 156 598 231 598Z"></path></g><g transform="matrix(.013,0,0,-0.013,29.602,0)"><path d="M275 270C275 450 212 609 64 710L45 686C145 604 203 442 203 270S147 -63 45 -147L64 -170C213 -68 275 89 275 270Z"></path></g></svg></td><td class="align_center">RMSE <svg height="13.8595pt" id="M168" style="vertical-align:-2.2681pt" version="1.1" viewbox="-0.0498162 -11.5914 34.2622 13.8595" width="34.2622pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M300 -147C201 -63 143 98 143 270S200 602 300 686L282 710C136 610 70 450 70 271V270C70 89 136 -72 282 -170L300 -147Z"></path></g><g transform="matrix(.013,0,0,-0.013,4.498,0)"><path d="M528 54L331 254L528 455L492 493L294 291L96 493L60 455L257 254L60 54L96 16L294 217L492 16L528 54Z"></path></g><g transform="matrix(.013,0,0,-0.013,12.129,0)"><path d="M384 0V27C293 34 287 42 287 114V635C232 613 172 594 109 583V559L157 557C201 555 205 550 205 499V114C205 42 199 34 109 27V0H384Z"></path></g><g transform="matrix(.013,0,0,-0.013,18.369,0)"><path d="M241 635C89 635 35 457 35 312C35 153 89 -12 240 -12C390 -12 443 166 443 312C443 466 390 635 241 635ZM238 602C329 602 354 454 354 312C354 172 330 22 240 22C152 22 124 173 124 313S148 602 238 602Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,24.656,-5.741)"><path d="M247 635C116 635 39 518 39 421C39 315 113 237 221 237C239 237 258 241 281 253L349 289C315 140 204 42 60 19L66 -15C90 -15 153 -5 207 16C344 70 447 199 447 385C447 521 373 635 247 635ZM231 598C329 598 356 478 356 390C356 371 355 347 352 325C330 309 297 297 262 297C179 297 127 369 127 456C127 515 156 598 231 598Z"></path></g><g transform="matrix(.013,0,0,-0.013,29.602,0)"><path d="M275 270C275 450 212 609 64 710L45 686C145 604 203 442 203 270S147 -63 45 -147L64 -170C213 -68 275 89 275 270Z"></path></g></svg></td><td class="align_center">MAPE</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">Meta-TFX11</td><td class="align_center">2.36</td><td class="align_center">3.95</td><td class="align_center">0.1652</td></tr><tr><td class="align_left">Meta-TFVMD</td><td class="align_center">2.17</td><td class="align_center">2.62</td><td class="align_center">0.1561</td></tr><tr><td class="align_left">Meta-TFWavelet</td><td class="align_center">2.25</td><td class="align_center">3.85</td><td class="align_center">0.1417</td></tr><tr><td class="align_left">Meta-TFSTL-w/o G</td><td class="align_center">2.11</td><td class="align_center">3.79</td><td class="align_center">0.1266</td></tr><tr><td class="align_left">Meta-TFSTL-w/o D</td><td class="align_center">2.13</td><td class="align_center">4.05</td><td class="align_center">0.1469</td></tr><tr><td class="align_left">Meta-TFSTL-w/o F</td><td class="align_center">2.29</td><td class="align_center">4.33</td><td class="align_center">0.1348</td></tr><tr><td class="align_left"><b>Meta-TFSTL</b></td><td class="align_center"><span style="width: 21.5518ptpx;"><svg height="8.62698pt" id="M169" style="vertical-align:-0.1933403pt" version="1.1" viewbox="-0.0498162 -8.43364 21.5518 8.62698" width="21.5518pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M345 0V33C260 38 258 46 258 122V635C174 612 105 594 35 583V554L87 550C124 546 130 539 130 494V122C130 46 127 38 42 33V0H345Z"></path></g><g transform="matrix(.013,0,0,-0.013,4.81,0)"><path d="M126 -12C170 -12 201 19 201 64C201 108 170 140 127 140C85 140 53 108 53 64C53 19 85 -12 126 -12Z"></path></g><g transform="matrix(.013,0,0,-0.013,8.112,0)"><path d="M496 176V231H406V629H337C242 511 133 363 25 211V176H279V113C279 53 274 40 189 33V0H487V33C413 40 406 49 406 109V176H496ZM279 231H103C166 334 228 422 277 488H279V231Z"></path></g><g transform="matrix(.013,0,0,-0.013,14.911,0)"><path d="M463 623H53C46 580 40 529 27 451H59C87 510 95 515 162 515H378C293 352 192 176 75 1L82 -12L186 0C277 205 377 410 472 611L463 623Z"></path></g></svg></span></td><td class="align_center"><span style="width: 23.3003ptpx;"><svg height="8.67266pt" id="M170" style="vertical-align:-0.2390203pt" version="1.1" viewbox="-0.0498162 -8.43364 23.3003 8.67266" width="23.3003pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M442 172C405 109 393 108 333 108H171L289 222C383 315 430 374 430 457C430 569 349 635 249 635C187 635 134 610 97 573L34 478L61 455C93 502 136 542 196 542C265 542 300 491 300 422C300 346 261 273 191 190C142 132 84 76 31 25V0H432C443 42 455 105 471 163L442 172Z"></path></g><g transform="matrix(.013,0,0,-0.013,6.422,0)"><path d="M126 -12C170 -12 201 19 201 64C201 108 170 140 127 140C85 140 53 108 53 64C53 19 85 -12 126 -12Z"></path></g><g transform="matrix(.013,0,0,-0.013,9.724,0)"><path d="M269 635C116 635 39 509 39 420C39 315 112 231 232 231C249 231 265 236 289 248L339 275C313 154 211 45 63 18L68 -15C112 -14 199 2 238 18C385 75 486 213 486 384C486 519 414 635 269 635ZM247 596C325 596 350 485 350 388C350 371 349 347 345 313C331 307 315 300 290 300C217 300 171 375 171 460C171 520 190 596 247 596Z"></path></g><g transform="matrix(.013,0,0,-0.013,16.653,0)"><path d="M463 623H53C46 580 40 529 27 451H59C87 510 95 515 162 515H378C293 352 192 176 75 1L82 -12L186 0C277 205 377 410 472 611L463 623Z"></path></g></svg></span></td><td class="align_center"><span style="width: 34.6266ptpx;"><svg height="8.62698pt" id="M171" style="vertical-align:-0.1933403pt" version="1.1" viewbox="-0.0498162 -8.43364 34.6266 8.62698" width="34.6266pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M264 635C97 635 40 460 40 311C40 167 94 -12 262 -12C431 -12 484 166 484 312C484 457 431 635 264 635ZM261 595C330 595 347 450 347 314C347 174 330 28 263 28C195 28 177 174 177 315C177 450 194 595 261 595Z"></path></g><g transform="matrix(.013,0,0,-0.013,6.812,0)"><path d="M126 -12C170 -12 201 19 201 64C201 108 170 140 127 140C85 140 53 108 53 64C53 19 85 -12 126 -12Z"></path></g><g transform="matrix(.013,0,0,-0.013,10.114,0)"><path d="M345 0V33C260 38 258 46 258 122V635C174 612 105 594 35 583V554L87 550C124 546 130 539 130 494V122C130 46 127 38 42 33V0H345Z"></path></g><g transform="matrix(.013,0,0,-0.013,15.015,0)"><path d="M264 635C97 635 40 460 40 311C40 167 94 -12 262 -12C431 -12 484 166 484 312C484 457 431 635 264 635ZM261 595C330 595 347 450 347 314C347 174 330 28 263 28C195 28 177 174 177 315C177 450 194 595 261 595Z"></path></g><g transform="matrix(.013,0,0,-0.013,21.827,0)"><path d="M463 623H53C46 580 40 529 27 451H59C87 510 95 515 162 515H378C293 352 192 176 75 1L82 -12L186 0C277 205 377 410 472 611L463 623Z"></path></g><g transform="matrix(.013,0,0,-0.013,27.597,0)"><path d="M496 176V231H406V629H337C242 511 133 363 25 211V176H279V113C279 53 274 40 189 33V0H487V33C413 40 406 49 406 109V176H496ZM279 231H103C166 334 228 422 277 488H279V231Z"></path></g></svg></span></td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr><tr class="table-fn"><td><div>The bold value indicates best result.<br/></div></td></tr></table>

<div>Ablation study results for imports.</div>

International Journal of Intelligent Systems

tab5

Table 5

Table 5: Meta-Learning Enhanced Trade Forecasting: A Neural Framework Leveraging Efficient Multicommodity STL Decomposition 