1. Home
  2. Article Catalog

Explore Our Developer Content



Viewing 1-10 of 338

Learn Refinitiv WebSocket APIs with Postman
This article demonstrates how to use Postman to establish WebSocket connections to Refinitiv Real-Time products to retrieve or contribute real-time financial data.

Apply Maximum Drawdown Daily Report for Fund Holding
Maximum Drawdown (MDD) is an indicator of downside risk, with large MDDs suggesting that down movements could be volatile. However, while MDD measures the largest loss, it does not account for the frequency of losses and the size of any gains.

Getting Start Unit Test for an HTTP REST Application with Python
This article shows how to run unit test cases for a Python application that performs HTTP REST operations.

Running Google BigQuery SQL inside VS Code
A brief guide to the BiqQuery Runner extension for VS Code and how to use it with a Refinitiv Tick History Google Cloud System account

EDA for Time Series Data using PyCaret
In this article, we are going to ingest time-series data using the Refinitiv Data Library and perform exploratory data analysis using the beta version of Pycaret, a “low-code” library that can be used to significantly decrease research and experimentation time. This can be done through various

Feature Engineering - Imputation, Scaling, Outliers
This blueprint discusses basic feature engineering steps such as imputation, scaling and outlier detection.

Modelling and Evaluation using PyCaret on Time Series Data
This article is the second in a series and in our previous one, we performed Exploratory Data Analysis on time series data loaded using the Refinitiv Data library and PyCaret. In this article, we will make use of the AutoML functions available in PyCaret, to generate an evaluate an optimal

Modelling and Evaluation – Proprietary models using Tensorflow & Keras – Part I
While the out-of-the box structures provided from Tensorflow are more than enough to cover most of the AI scenarios, sometimes we need to implement a fully proprietary AI structure that solves a specific problem.

Feature Engineering - Synthetic Data with Generative Adversarial Networks
Data can sometimes be difficult to find or expensive and time-consuming to acquire. Furthermore, data can be sensitive and difficult to share. In such situations, Generative Adversarial Networks (GAN)s can be a valuable tool. Artificially recreating a dataset is a complex and sensitive process.

Data Engineering - Data ingestion for M&A predictive modeling
This article focuses on the ingestion phase of an AI pipeline analysing corporate events. Corporate events, such as M&A or bankruptcy announcements, can result in substantial stock price changes. Academic research has shown evidence of significant abnormal returns for target company stocks, making