# Xin Dong

Xin Dong is a remote worker on Himalayas, Machine Learning Scientist Intern at Wayfair, based in United States.

Source: https://himalayas.app/@xindong

```text
Applied scientist who improved Amazon Ads purchase prediction ROC-AUC by 7.5% over production baselines.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | United States |
| Authorized to work in | United States |
| Salary expectations | 60k+ USD |
| Job categories | Applied Scientist, Machine Learning Scientist |
| Skills | predictive modeling, Sequence Modeling, Transformer Models, Multi Touch Attribution, Causal Inference, Model Evaluation, Large Language Models, Reinforcement Learning, Demand Forecasting, Optimization, Shapley Attribution, Distributed Training, Machine Learning Pipelines, Python, SQL |
| LinkedIn | https://linkedin.com/in/xindong2026 |

## About

```text
At Amazon, I adapted pretrained Transformers for Ads measurement, building a modeling pipeline from 10M temporally aligned searches, ad impressions, and purchases. The framework improved off-Amazon purchase prediction ROC-AUC by 7.5% over production baselines and extended to customer-level Shapley attribution.

At Wayfair, I enhanced the Multi-Touch Attribution system with an end-to-end feature enrichment pipeline. Evaluations validated against 6 geo-lift experiments reduced attribution error by $3.13M (10.7%), while productionized Airflow workflows reduced model runtime by 14%.

My research includes LLM evaluation, spatio-temporal demand forecasting, and reinforcement learning for bus operations. In a bus-holding project, the framework reduced headway variability by 32.0%, bus bunching by 69.2%, and passenger waiting time by 24.0% over the best calibrated rule-based baseline.
```

## Experience

### Machine Learning Scientist Intern

[Wayfair](https://himalayas.app/companies/wayfair-inc). Jun 2026 - Aug 2026

```text
Enhanced Wayfair's Multi-Touch Attribution system for measuring incremental revenue impact across marketing channels. Built an end-to-end feature enrichment pipeline and productionized Airflow-based ML workflows.
```

Skills: Airflow, Feature-Engineering, Model-Evaluation, Causal-Inference, Python, Attribution-Modeling

### Applied Scientist Intern

[Amazon](https://himalayas.app/companies/amazon). May 2025 - Aug 2025

```text
Adapted decoder-based pretrained Transformers to Ads measurement, developing a unified framework for conversion prediction, attribution, and incremental lift estimation. Built an end-to-end modeling pipeline and scaled billion-parameter Transformer fine-tuning on AWS.
```

Skills: Transformers, AWS, LoRAs, Distributed-Training, PyTorch, Ads-Measurement, Attribution-Modeling

## Education

### Penn State University

Doctor of Philosophy, Operations Research & Civil Engineering. 2022 - Present. Grade: 3.9/4.0

```text
Ph.D. candidate in Operations Research and Civil Engineering with a GPA of 3.9/4.0, expected to graduate in May 2027.
```

### Georgia Institute of Technology

Master of Science, Computer Science. 2024 - Present

```text
M.S. in Computer Science, expected to graduate in May 2027.
```

### University of Michigan

Master of Science, Civil Engineering. 2018 - 2020

```text
M.S. in Civil Engineering from 2018 to 2020.
```

### Southeast University

Bachelor of Science, Civil Engineering. 2014 - 2018

```text
B.S. in Civil Engineering, including an exchange at the University of Tennessee, from 2014 to 2018.
```

## Tech stack

- PySpark
- Python
- Java
- C++
- TensorFlow
- PyTorch
- scikit-learn
- Docker
- Airflow
- SQL
- Hugging Face
- LangChain
- AutoGen
- vLLM
- Cursor
- LangGraph
- Gurobi
- AWS
- Azure

To contact Xin, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Yuying Liu](https://himalayas.app/@yuyingliu): Applied Scientist II, Amazon
- [Pratik Sannakki](https://himalayas.app/@pratiksannakki): Data Scientist, AbbVie Inc.
- [Han Zhang](https://himalayas.app/@hanzhang): Senior Machine Learning Engineer, Instacart
- [Jacob Miller](https://himalayas.app/@jacobmiller2): Data Scientist, Meta
- [Karmabir Chakraborty](https://himalayas.app/@karmabirchakraborty): Data Analyst, LS Direct
- [Richard Davis](https://himalayas.app/@richarddavis5): Senior Data Scientist, Uber
- [Aayush User](https://himalayas.app/@aayushuser14): Advanced Machine Learning Teaching Assistant, University of Maryland, College Park
- [Kevin Shi](https://himalayas.app/@kevinshi1): Senior Machine Learning Engineer, Netflix
- [Anthony Chen](https://himalayas.app/@anthonychen): Senior Machine Learning Engineer, Google
- [Sai Niharika Kukatla](https://himalayas.app/@sainiharikakukatla): Data Scientist – ML Engineer, Walmart