Ruochi Zhang

I am a Phd student of Jilin Univerity. My reasearch area focuses on the data mining algorithms for the biomedical big data. Specifically, developing efficient feature selection, feature engineering and prediction algorithms for the high-dimensional biomedical data.

I have great enthusiasm for the application of AI in the industry. In my personal work and internship experience, I was responsible for data platform, natural language processing platform, knowledge graph, OCR engine, etc. in some financial technology companies. I have also researched molecular generation, molecular property prediction, and compound structure recognition in AI pharmaceutical companies. I am very interested in the application of AI in various fields, and constantly exploring what value AI can play in society.


  • Jilin University, China.
    • Phd in Computer Science and Technology
    • Sep, 2020 - Present
  • University of Pittsburgh, US.
    • Sep. 2018 - Present
    • M.S in Information Science
    • Cumulative GPA: 3.92/4.0
  • Jilin University, China.
    • Bachelor in Computer Science and Technology
    • Sep, 2014 - Jun, 2018

Publications (* means co-first authors)

  • Ruochi Zhang, hehao Guo, Yue Sun. COVID19XrayNet: a two-step transfer learning model for the COVID-19 detecting problem based on a limited number of chest X-ray images. Computational Life Sciences , Aug. 2020
  • Haochen Yao*, Nan Zhang*, Ruochi Zhang*. Severity detection for the coronavirus disease 2019 (COVID-19) patients using a machine learning model based on the blood and urine tests. Frontiers in Cell and Developmental Biology. July. 2020 Download
  • Ruochi Zhang, Ruixue Zhao, Fengfeng Zhou. pyHIVE, a Health-related Image Visualization and Engineering system using Python. BMC Bioinformatics, Nov. 2018 Download here
  • Ruixue Zhao*, Ruochi Zhang*, Fengfeng Zhou. TriZ-a rotation-tolerant image feature and its application in endoscope-based disease diagnosis. Computers in Biology and Medicine, Aug. 2018’ Download here
  • Fengxin, Ruochi Zhang, Fengfeng Zhou. An accurate regression of developmental stages for breast cancer based on transcriptomic biomarkers. Biomarkers in Medicine, Oct. 2018 Download here
  • Yuting Ye*, Ruochi Zhang*, Weiwei Zheng, Shuai Liu & Fengfeng Zhou. RIFS: A Randomly Restarted Incremental Feature Selection Algorithm. Scientific Reports, Sept. 2017 Download here
  • Ruiquan Ge*, Guoqin Mai*, Ruochi Zhang*, Xundong Wu, Qing Wu, Fengfeng Zhou. MUSTv2: An Improved De Novo Detection Program for Recently Active Miniature Inverted Repeat Transposable Elements (MITEs). Journal of Integrative Bioinformatics, May 2017 Download here

Work Experience

Beijing XDstar Technology Co., Ltd. Beijing | Jan 2018 - Present

Technical Co-founder

  1. Risk strategy, risk management, anti-fraud strategy
    • keywords: Neo4j、Sequence model、Convolutional Neural Network、Graph deep Learning、Fraud detection.
  2. Anomaly detection
    • keywords: Sampling、Clustring、Isolation forest、LSTM/GRU.
  3. Natural Language Processing Platform
    • keywords: Word2Vec、Seq2Seq and Attention、Contextual Word Representations、Machine Translation、 Transfer Learning.

Fulmz Technology | Aug 2020 - Present

Algorithm Engineer, Data Scientist

  • Natural Language Processing
  • Use Artificial Intelligence technology to find new drugs, the main direction is the prediction of molecular properties and molecular generation. It involves graph neural network, Transformer, Sequence model, Reinforcement Learning, etc.

Changchun Wanyi Technology | June 2020 - Aug 2020

Algorithm Engineer

  1. OCR recognition algorithm
  2. Financial text data analysis and algorithm design
  3. Model service backend
  4. Wanyi brain technology route and architecture design

Intel. | May 2019 - Aug 2019

Deep Learning Software Engineer Intern , Big Data Tech Architecture

  • Design and implement the architecture of Zoo Serving (Analytics-Zoo)

Shanghai Institute of Life Sciences. | Apr 2017 - Oct 2017

Algorithm Research Assistant Shanghai

  1. Design dynamic network biomarker algorithms and single-sample dynamic network algorithms
  2. Parallel computing



  • 专利号:2019106169425
    本发明的实施方式提供了一种交易数据的异常检测方法、介质、装置和计算设备。该方法包括: 基于预先获得的交易数据生成知识图谱;知识图谱的节点用于表示交易数据中的账户实体,两个节点之间的边用于表示两个节点分别对应的账户实体之间的交易关系;利用图神经网络对知识图谱进行图深度学习,得到知识图谱中每条边的特征表示,并将边的特征表示确定为边对应的交易数据的特征向量;将预先确定的待检测交易数据的特征向量输入利用交易数据的特征向量训练得到的神经网络模型,经过神经网络模型的处理后,输出待检测交易数据的检测结果。



  • Professional Emphasis: Data Mining, Machine Learning, Deep Learning, Data Analysis
  • Language: Python, Ruby, Java, C, Matlab, R, JavaScript, Shell
  • Framework: NumPy, Pandas, Scikit-Learn, MXNet, Keras, NetworkX, Matplotlib Database: MySql, Neo4j, ElasticSearch
  • Coursera Certificate: https://github.com/zhangruochi/Master-Computer-Science

Leave messages to me at here