7. Deep Learning to Perform Causal Inference - [E2] Pham, Thai T. and Yuanyuan Shen. 2017

[lkcao]

Post questions here for this week's exemplary readings:

2. Pham, Thai T. and Yuanyuan Shen. 2017. “A Deep Causal Inference Approach to Measuring the Effects of Forming Group Loans in Online Non-profit Microfinance Platform”. arXiv.org preprint: 1706.02795.

[XiaotongCui]

The paper employs GloVec pre-trained word vectors, trained on Wikipedia data, as the fixed representations of words in our models. However, given that we are analyzing text within the microfinance domain, there is a concern that directly utilizing a pre-trained model trained on "general text field" data may introduce biases.

[anzhichen1999]

The paper addresses the strong performance of these models on predictive natural language tasks in various contexts, as evidence of their effectiveness in extracting relevant information for prediction tasks. However, how does the best available language model be addressed here by the second assumption?

[joylin0209]

The application of deep learning techniques to process and analyze loan descriptions for causal inference caught my attention. But I'm curious, what are the potential limitations or challenges of these techniques in accurately capturing the nuances of textual data in different languages or cultural contexts?

[YucanLei]

the study primarily examines the impact of group loans on funding time, but it may not fully address the broader implications of group lending on borrower outcomes or the long-term sustainability of microfinance initiatives. Further research could explore these aspects to provide a more comprehensive understanding of the effects of group loans in online microfinance settings.