Data beats opinion >>> your weekly update on the alternative data space

1. Dataset of the week: Email purchase receipts data provider.

2. Case study: Google Trends anticipated Tableau stabilization.

3. Case study: Predicting Chinese auto revenues using alternative data.

4. Engineering: A guide to structured web data.

5. News articles of the week: GS to let AI make investment choices, Sentient Technologies, Wes McKinney pushes Big Data interoperability.

6. Eagle Alpha’s NYC event – legal & compliance considerations.

1. Dataset of the week: Email purchase receipts data provider.

Vendor Overview: This vendor provides anonymized purchase data from more than 1.5 million active U.S. consumers, scanned from email purchase receipts. Covers over 550 merchants from more than 25 industries.

Dataset Overview:

  • History: Since 2013.
  • Geography: United States.
  • Delivery: API or CSV.
  • Frequency: Weekly.

Alpha Use Cases:

  • Track sales indicators that could be incorporated in revenue predictive models.
  • Create a cohort of constant panelists to analyze their purchase behavior over time.


Our database now has 489 providers. Contact us for more information –
enquiries@eaglealpha.com

2. Case study: Google Trends anticipated Tableau stabilization

On 5 January 2017, we published a research note showing that our Google Index indicated early signs of stabilization for Tableau. The figure 2 below shows that the initial decline of the 3m index below the 12m index was a lead indicator for slower trends 4 to 5 quarters later, so the movement over the last two quarters was seen as a potential action point for a change in company fundamentals in future quarters.

On 2 February 2017, Tableau reported Q4 and Full Year results beating revenue and EPS.

Contact us to learn about our “Search Signals” offering – enquiries@eaglealpha.com.

3. Case Study: Predicting Chinese auto revenues using alternative data

On 6 February 2017, we demonstrated the value of Eagle Alpha’s China Auto Insight (CAI) dataset when analyzing the Chinese auto industry.

The CAI data showed a 99% correlation with Great Wall revenue and a 95% correlation with YoY revenue growth over a 5-year period. The calculated dealership revenue also correctly projected the directional movement of reported revenues for Great Wall in fourteen of the fifteen quarters between Q1 2013 and Q3 2016.

An autoregressive model for predicting Great Wall Motors revenue, incorporating CAI data, demonstrated a mean absolute percentage error (MAPE) of just 4.9%. This compares to a MAPE of 10.3% on a baseline autoregressive model using just historic revenues. The error rate for market consensus estimates was 8.1% over the same period.

In Q4 2014, the CAI data was more accurate than consensus estimates at predicting an important inflection in revenue growth. Analyst estimates were for QoQ revenue growth by 17% for Great Wall Motors, compared to reported QoQ growth of 42%. Estimated QoQ growth based on the CAI raw data was 48%.


4. Engineering: A guide to structured web data

The recent white paper prepared by Webhose.io, a company providing access to structured web data, gives an overview of technological issues associated with extracting web data from various and fragmented sources.

The white paper discusses how Webhose.io extracts web data and identifies each crawled source as a “post”, how it then creates inferred and enriched fields so that web data can be analyzed for deeper insights.

More processing power is required to produce enriched fields, but these are helpful for understanding deeper meanings and trends. For example, “Fox” can be referred to different entities, e.g. organization, personality, location or animal. Furthermore, this field could also be enriched by associating a specific sentiment score to it.

5. News articles of the week: GS to let AI make investment choices, Sentient Technologies, Wes McKinney pushes Big Data interoperability

Goldman Sachs to let AI make investment choices in Japan.

Silicon Valley Hedge Fund Takes On Wall Street With AI Trader.

Hedge fund technology guru Wes McKinney pushes big data interoperability.

6. Eagle Alpha’s NYC event – legal & compliance considerations

Morning of 26th April 2017 – Discussion of legal and compliance considerations e.g. privacy policy, PII, web crawling, exclusivity etc. Our event partners are Lowenstein Sandler and the ACA Compliance Group.

Until next week,

Eagle Alpha.

www.eaglealpha.com