Track China's economic activity daily

Leverage real-time news sentiment, alternative data, and macroeconomic variables to project GDP growth.

The RavenPack China GDP Nowcasting model leverages proprietary machine learning models to deliver a prediction of China’s Economic Activity: The Nowcasting model predicts, on a daily basis, the China GDP growth rate for the previous quarter Q–1 (Backcast), the current quarter Q (Nowcast), and the next Q+1, Q+2, Q+3, and Q+4 quarters (Forecasts). Beside macro variables and sentiment scores, the model also draws from a broad range of alternative data sources, from freight to electricity production. Principal components are presented similar to a PMI index to better capture any sudden changes in the data.

Leverage

A Unique Vantage Point on the Chinese Economy

The RavenPack China GDP Nowcast leverages datapoints beyond macroeconomic variables such as:

  • Industrial Production including tires, clothes, iron, and yarn
  • Trade as import
    and export
  • Freight in terms of freight volume, turnover, and exports
  • Surveys of services and manufacturing PMI
  • Electricity consumption
  • Retail Sales and Vehicle Sales
  • Traffic as volume of passengers and passenger turnover

as well as over 20 distinct macroeconomic factors. The model provides information about which variables altered the final prediction, and the magnitude of its impact. Follow the forecast line to find out more:

Follow the forecast line to find out more

This indicator can help quantitative and discretionary investors:

Nowcast Performance

The performance of the RavenPack China GDP Nowcasting model can be measured against a nowcasting Dynamic Factor Model based solely on macroeconomic variables in a run-up against the benchmark of an auto-regressive model. The model that produces the RavenPack nowcast improves on the DFM model by up to 9%, and produces more accurate predictions as early as 22 weeks before official figures are released.

Prediction error of an auto-regressive model (AR1) Dynamic Factor Model based on Macroeconomic Variables 50% betterthan benchmark 75% betterthan benchmark 25% betterthan benchmark Benchmark Actual GDP Sentiment-enhanced Nowcasting model 1 week 4 weeks 8 weeks 14 weeks 17 weeks 22 weeks 26 weeks Time until the actual GDP is released FORECAST NOWCAST BACKCAST
'
UNDER THE HOOD

Computing China GDP predictions

Backcasts, nowcasts, and forecasts are the outcome of a multi-step process that includes:

Content Collection

RavenPack analyzes textual content from high-quality sources to identify events that are relevant to the Chinese economy. Documents considered include articles and press releases in English pertaining to specific economic narratives.

Information Extraction

Additional filters ensure the data remains focused on contemporary observations, and relevant organizations. In addition, events that relate to the comparison between expectations and actual economic figures are excluded to reduce noise.

Analytics Enrichment

For each event identified, RavenPack uses sentiment analysis to compute multiple scores by matching stories usually categorized by financial experts as having a positive or negative financial or economic impact.

Signal Construction

Sentiment scores are averaged and smoothed over time then introduced into a dynamic factor model as stationary monthly input variables with daily updates. Over 20 additional factors are also included, from macroeconomic data points to alternative data.

Model Output

The model produces predictions over 6 quarters, from backcast to forecast, with daily updates.

Nowcast Facts
Purpose
  • Improve timeliness & accuracy of economic predictions
  • Enhance asset and sector rotation
FrequencyDaily
HistorySince 2010
UniverseChina Macro
Content
  • When the prediction was produced, and when it will be effective (quarter end)
  • Latest and previous forecast
  • The macroeconomic variable(s) whose release or revision impacted the overnight prediction.
  • The evaluation method, Year over Year.
  • The previous and updated values of these variables, and the difference between predicted and actual value.
  • The contribution of the variable to the prediction, and the impact of the release.
  • The type of prediction: BACKCAST (previous quarter), NOWCAST (current quarter), FORECAST (next quarter), FORECAST2S (2 quarters ahead), FORECAST3S (3 quarters ahead) and FORECAST4S (4 quarters ahead).
Delivery RavenPack, Snowflake

Access the China GDP Nowcast


By providing your personal information and submitting your details, you acknowledge that you have read, understood, and agreed to our Privacy Statement and you accept our Terms and Conditions. We value your privacy and assure you that we will handle your personal information with the utmost care and in compliance with our Privacy Statement. You can exercise your rights of access, rectification, erasure, restriction of processing, data portability, and objection by emailing us at privacy@ravenpack.com. In accordance with the General Data Protection Rules (GDPR). You also are agreeing to receive occasional updates and communications from RavenPack about resources, events, products, or services that may be of interest to you.