Advanced in Financial machine learning : Part 2- Chapter 2: financial data structure

2.2 Essential types of financial data

4 types of data:

Fundamental dataMarket dataAnalytics dataAlternative data
AssetsPriceAnalyst recommendCCTV image
LiabilitiesVolumeCredit ratingsGoogle searches
SalesDividendEarning expectationTwitter Chats
EarningsOpen InterestNews sentimentMeta data
MacroQuotes

2.2.1 Fundamental data

Definition

Fundamental data encompasses information that can be found in regulatory filings and business analytics.

Characteristics

  1. The available time of the data is not at the end of period.
    • The first quarter financial report of AAPL is not publised on 01-Apr of the year, so if we set the available time of the fundamental data at the end of the first quarter, we might be involved in using future data and cause issue in future test and real trading
  2. Backfilled and reinstate of fundamental data
    • Some of the fundamental data might be missing or wrong at its initial release, so in the future, the missing data might be filled and wrong data might be corrected. If we still assign the available time of these data the same as rest of the data, we might be involved in using future data.
  3. Low frequent hence little value remained unexploited
    • Being so accessible to the marketplace, it is rather unlikely that there is much value left to be exploited. Still, it may be useful in combination with other data types.

Market Data

Definition

Market data includes all trading activity that takes place in an exchange (like CME) or trading venue (like MarketAxess).

Characteristics

  1. Data provider has given you a raw feed, which could be difficult to process
    • Data provider has given you a raw feed, with all sorts of unstructured information, like FIX messages that allow you to fully reconstruct the trading book, or the full collection of BWIC (bids wanted in competition) responses
  2. Market Data could be very abundant and storage could be a problem.

Analytic Data

Definition

You could think of analytics as derivative data, based on an original source, which could be fundamental, market, alternative, or even a collection of other analytics.

Characteristics

  1. The negative aspects are that analytics may be costly, the methodology used in their production may be biased or opaque, and you will not be the sole consumer.

Alternative Data

Definition

  1. Alternative data was differentiated by:
    • Produced by individual ( social media, news etc.)
    • Business process ( transaction, corporate data, government agency etc.)
    • sensors( satellites, geolocation, weather etc.)

Characteristics

  1. alternative data is that it is primary information, that is, information that has not made it to the other sources.
  2. Two problematic aspects of alternative data
    • Cost
    • Privacy

Leave a comment