CoGSeq-LTV: Scalable Missing-Aware Graph-Sequence Modeling for Multi-Business Transaction Analytics
Organizations: School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Tencent WeChat Pay Research and Development Department, Shenzhen, China
Abstract
Large-scale super-apps generate heterogeneous transaction logs in which users interact with multiple businesses, item identifiers are only partially available, and future value targets are sparse, heavy-tailed, and cumulative over time. We study multi-business, multi-horizon value prediction as a data-intensive analytics problem over such logs, rather than as a single-table task. (i) a batch-induced user-item graph that provides collaborative signals without materializing a global graph and remains applicable when item identifiers are missing through reserved unknown-item handling, (ii) business-aware sequence encoders that preserve recency, inter-event gaps, payment context, and goods-table availability, and (iii) cross-view contrastive alignment that transfers user-level intent across businesses while retaining business-specific temporal patterns. To handle zero-inflated and long-tailed cumulative targets, CoGSeq-LTV adopts a zero-inflated mixture log-normal head with MAE-aligned point supervision and validation-calibrated zero-aware inference. Experiments on the BiBiSheng transaction-log dataset show that CoGSeq-LTV improves over representative LTV baselines across businesses and horizons, including under a later out-of-time evaluation window.
Figures & tables
| Statistic | Value | Statistic | Value |
| #Users | 4,850,141 | #Total records | 41,842,772 |
| #In-domain items | 1,159,378 | #In-domain records | 19,067,648 |
| #E-commerce (ch. 237) | 10,452,694 | #Food delivery (ch. 689) | 31,390,078 |
| Channel | #Records (%) | Domain | Coverage |
| 2 (JD) | 6,597,985 (15.8%) | In | 100% |
| 3 (VIP) | 399,327 (1.0%) | In | 100% |
| Horizon | Metric | Model | |||||||
|---|---|---|---|---|---|---|---|---|---|
| ZILN ( Wang et al., 2019 ) | ODMN ( Li et al., 2022 ) | perCLTV ( Zhao et al., 2023 ) | OptDist ( Weng et al., 2024 ) | expLTV ( Zhang et al., 2023 ) | MEAN ( Liu et al., 2025 ) | MDAN ( Liu et al., 2024 ) | CoGSeq-LTV | ||
| 7 | MAE | 683.47 42.15 | 371.04 58.32 | 614.25 61.47 | 542.17 45.81 | 512.39 41.26 | 324.96 38.54 | 305.28 37.19 | 261.55 39.43 |
| WAPE | 1.872 0.022 | 1.165 0.035 | 1.628 0.038 | 1.618 0.024 | 1.548 0.021 | 1.082 0.019 | 0.992 0.018 | 0.944 0.020 | |
| 14 | MAE | 3346.55 115.42 | 1588.39 152.63 | 2776.92 168.91 | 2315.42 121.37 | 2197.84 118.54 | 1503.27 105.28 | 1342.71 102.16 | 1040.59 107.85 |
| WAPE | 1.894 0.032 | 1.229 0.048 | 1.589 0.051 | 1.722 0.035 | 1.635 0.031 | 1.097 0.028 | 1.020 0.027 | 0.948 0.030 | |
| 30 | MAE | 5432.74 135.82 | 2763.75 185.47 | 4912.48 192.36 | 3964.81 142.19 | 3768.15 138.65 | 2436.52 125.43 | 2279.56 122.81 | 1897.07 127.15 |
| Horizon | Metric | Model | |||||||
|---|---|---|---|---|---|---|---|---|---|
| ZILN ( Wang et al., 2019 ) | ODMN ( Li et al., 2022 ) | perCLTV ( Zhao et al., 2023 ) | OptDist ( Weng et al., 2024 ) | expLTV ( Zhang et al., 2023 ) | MEAN ( Liu et al., 2025 ) | MDAN ( Liu et al., 2024 ) | CoGSeq-LTV | ||
| 7 | MAE | 711.34 14.52 | 458.27 28.45 | 651.68 35.12 | 671.39 12.84 | 634.81 11.36 | 415.73 8.45 | 381.42 6.12 | 365.61 4.69 |
| WAPE | 1.895 0.012 | 1.138 0.025 | 1.662 0.031 | 1.654 0.015 | 1.582 0.011 | 1.087 0.009 | 0.982 0.007 | 0.948 0.004 | |
| 14 | MAE | 1715.62 32.15 | 1032.51 65.34 | 1553.17 82.19 | 1402.53 28.41 | 1328.46 25.63 | 962.18 21.05 | 879.15 18.34 | 826.87 19.81 |
| WAPE | 1.972 0.018 | 1.170 0.038 | 1.648 0.042 | 1.687 0.016 | 1.611 0.014 | 1.041 0.012 | 0.968 0.011 | 0.926 0.010 | |
| 30 | MAE | 3823.18 68.42 | 2315.92 145.67 | 3279.34 186.23 | 3468.15 55.18 | 3291.37 52.34 | 2087.45 42.15 | 1885.07 38.62 | 1793.41 39.96 |
| Business | Horizon | Metric | Model/Variants | ||||
|---|---|---|---|---|---|---|---|
| w/o User-Item Graph | w/o Contrastive Loss | w/o ZIMLN Module | w/o MAE-aligned | CoGSeq-LTV | |||
| E-commerce | 7 | MAE | 425.34 | 312.45 | 335.18 | 352.67 | 289.43 |
| WAPE | 1.2541 | 0.9912 | 1.0456 | 1.1123 | 0.9583 | ||
| 14 | MAE | 1815.47 | 1368.74 | 1425.36 | 1512.89 | 1299.69 | |
| WAPE | 1.2845 | 1.0125 | 1.0678 | 1.1567 | 0.9689 | ||
| 30 | MAE | 3138.41 | 2315.42 | 2458.91 | 2615.34 | 2199.11 | |
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
| Business | Horizon | Metric | Model | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| ZILN ( Wang et al., 2019 ) | ODMN ( Li et al., 2022 ) | perCLTV ( Zhao et al., 2023 ) | OptDist ( Weng et al., 2024 ) | expLTV ( Zhang et al., 2023 ) | MEAN ( Liu et al., 2025 ) | MDAN ( Liu et al., 2024 ) | CoGSeq-LTV | |||
| E-commerce | 7 | MAE | 743.80 | 371.04 | 665.44 | 536.84 | 281.92 | 322.59 | 279.35 | 274.68 |
| WAPE | 2.1753 | 1.2750 | 1.8642 | 1.7711 | 1.1518 | 1.1920 | 1.1469 | 1.1481 | ||
| 14 | MAE | 3694.30 | 1572.14 | 3008.71 | 2290.44 | 1244.80 | 1470.11 | 1233.92 | 1224.73 | |
| WAPE | 2.2583 | 1.3417 | 1.8621 | 1.8933 | 1.1627 | 1.2114 | 1.1694 | 1.1586 | ||
| 30 | MAE | 5965.29 | 2747.23 | 5275.38 | 3914.75 | 2111.36 | 2384.61 | 2105.97 | 2108.64 | |
| Business | Horizon | Metric | Model | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| ZILN ( Wang et al., 2019 ) | ODMN ( Li et al., 2022 ) | perCLTV ( Zhao et al., 2023 ) | OptDist ( Weng et al., 2024 ) | expLTV ( Zhang et al., 2023 ) | MEAN ( Liu et al., 2025 ) | MDAN ( Liu et al., 2024 ) | CoGSeq-LTV | |||
| E-commerce | 7 | MAE | 807.32 | 417.75 | 738.48 | 619.84 | 331.26 | 365.04 | 326.88 | 321.74 |
| WAPE | 2.1671 | 1.2729 | 1.8512 | 1.7610 | 1.0614 | 1.1793 | 1.0558 | 1.0496 | ||
| 14 | MAE | 4004.68 | 1778.64 | 3355.18 | 2640.71 | 1468.30 | 1671.70 | 1449.62 | 1436.18 | |
| WAPE | 2.2413 | 1.3445 | 1.8421 | 1.8895 | 1.0705 | 1.2029 | 1.0667 | 1.0601 | ||
| 30 | MAE | 6498.13 | 3103.75 | 5911.41 | 4473.83 | 2472.15 | 2724.86 | 2490.36 | 2458.27 | |
| Business | Horizon | Metric | Model | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| ZILN ( Wang et al., 2019 ) | ODMN ( Li et al., 2022 ) | perCLTV ( Zhao et al., 2023 ) | OptDist ( Weng et al., 2024 ) | expLTV ( Zhang et al., 2023 ) | MEAN ( Liu et al., 2025 ) | MDAN ( Liu et al., 2024 ) | CoGSeq-LTV | |||
| E-commerce | 7 | MAE | 765.23 | 385.12 | 685.41 | 561.38 | 532.14 | 338.45 | 345.67 | 295.12 |
| WAPE | 2.0541 | 1.1895 | 1.7542 | 1.6451 | 1.5782 | 1.1024 | 1.0543 | 0.9652 | ||
| 14 | MAE | 3785.14 | 1635.21 | 3105.42 | 2385.16 | 2265.41 | 1545.62 | 1485.67 | 1315.48 | |
| WAPE | 2.1245 | 1.2564 | 1.7456 | 1.7652 | 1.6745 | 1.1245 | 1.0856 | 0.9754 | ||
| 30 | MAE | 6124.53 | 2845.61 | 5456.21 | 4085.16 | 3885.42 | 2512.38 | 2545.12 | 2235.64 | |
Sequence Modeling
Sequence modeling studies how to represent, predict, classify, and generate ordered data such as text, time series, events, and biological sequences.
See all 268 papers