The Causal Learning of Retail Delinquency
Authors: Yiyan Huang, Cheuk Hang Leung, Xing Yan, Qi Wu, Nanbo Peng, Dongdong Wang, Zhixiang Huang204-212
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The proposed estimators are shown to be unbiased, consistent, and robust through a combination of theoretical analysis and numerical testing. Moreover, we compare the power of estimating the causal quantities between the classical estimators and the proposed estimators. The comparison is tested across a wide range of models, including linear regression models, tree-based models, and neural network-based models, under different simulated datasets that exhibit different levels of causality, different degrees of nonlinearity, and different distributional properties. Most importantly, we apply our approaches to a large observational dataset provided by a global technology firm that operates in both the e-commerce and the lending business. We find that the relative reduction of estimation error is strikingly substantial if the causal effects are accounted for correctly. |
| Researcher Affiliation | Collaboration | 1JD Digits 2City University of Hong Kong 3ISBD, Renmin University of China |
| Pseudocode | No | The paper describes mathematical formulations and derivations but does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link for open-source code for the methodology described. |
| Open Datasets | No | We now apply our method to a unique real-world dataset kindly provided by JD Digits, one of the largest global technology firms that operates in both the e-commerce business and the lending business. |
| Dataset Splits | No | All results are out-of-sample and we use 70% of data as the training set and the remaining 30% as the testing set. The paper does not explicitly state a separate validation split percentage or count. |
| Hardware Specification | Yes | The experiments are run on two Ubuntu HP Z4 Workstations each with Intel Core i9 10-Core CPU at 3.3GHz, 128G DIMM-2166 ECC RAM, and two sets of NVIDIA Quadro RTX 5000 GPU. |
| Software Dependencies | No | The paper mentions using Python for experiments but does not provide specific version numbers for Python or any other software libraries or dependencies. |
| Experiment Setup | Yes | The number of hidden layers ranges from 2 to 7 and the number of units for each layer from 50 to 500. The batch size is in integer multiples of 32 and optimized within [32, 3200]. We search the learning rate between 0.0001 and 0.1. |