Alternative Data

Discussion in 'Data Sets and Feeds' started by MoneyMatthew, May 8, 2018.

  1. I'm just a homer gamer non-institutional trader. Has anyone here dabbled around with "Alternative Data"? It seems to be a hot buzz word right now. The first generation of this stuff was centered around getting sentiment from social media and picking up on tweets before official news releases. I read a story about how a group of traders got long RBOB when a picture of a refinery on fire was tweeted and their special software picked it up before it became news and before the price spike occurred.

    Stuff like that is cool but what I am really interested in is this next generation of Alternative Data. You have people using realtime satellite imagery to measure shadows above oil refining holding tanks to estimate inventory before the official inventory numbers are released by the government. You have people looking at satellite photos of brick and mortar retailer's parking lots across the country to estimate success before earnings.

    The sources are endless, Railroad activity, anonyomized retail receipt data, IOT device reporting, Natural Resource cargo numbers, satellite photos ...it is just endless.

    Aside from thinking out loud in this post, I wonder how hard it would be to gather same stores sales data for every single location and then try to isolate which stores performance correlates with the quarterly earnings report? You could then just focus keeping an eye on a few locations to get a true leading indicator of the stock performance. This has already been done by flying satellites over every J.C. Penny location to count the number of cars in the parking lot. This type of thing just ain't accessible to the home gamers but it is a crystal ball in some instances.

    Looks like quandl has an offering:
    https://www.quandl.com/alternative-data
     
  2. What you are describing gives more value to technical analysis. It is the bigs boys with the big money who have these tools. However, it can take them a while to establish a reasonably sized position given their huge investment amounts.

    Hopefully a trader can see their "tracks" in the charts early enough to take advantage of a worthwhile opportunity.
     
  3. There's probably a lot to learn about how the markets are going by measuring the business at Wall Street liquor stores.
     
  4. jharmon

    jharmon

    Backtest it!
     
  5. I tried to get access to the alternative quandl data (I have two other subscriptions with them) but could not -its for institutions only (probably has a good price tag and possibly some decent alpha).
     
    MoneyMatthew likes this.
  6. tomorton

    tomorton

    Some alternative indicators have been around for a long time, haven't heard much about them recently. But that might just be because the market was just rising for years and years, so stock-picking fell from view.

    Worth thinking about -
    * company purchasing many new trucks
    * company starts heavy advertising
    * chairman and directors buying up shares
    * consumer footfall
    * staff recruitment drives
    * expanding to new sites
    * significant expansion into high profile sports etc. sponsorship
    * increased promotions at retail outlets / trade fairs
    * increased R&D investment (new development location, R&D staff recruitment)
    * new CEO or FOO appointed who has take-over track record
    etc.

    On the negative side, I once read that if the company's annual report features a photo showing the chairman alighting from a helicopter, this has become a vanity project and you should sell those shares immediately.
     
    MoneyMatthew likes this.
  7. Did they even try to sell you data or did they figure you did not have the bankroll from the start? Some of this data is compelling as a leading indicator well in advance of earnings.
     
  8. What I would like to do is track companies with CEOs who mask a bad quarter after a good quarter and maintain the street's earnings targets while falling short the next quarter and missing earnings. I would need some type of alternative data to confirm that things are not going well. B2B can screw with the numbers more, I think B2C is harder to hide bad earnings.
     
  9. Didn't even try to sell me the data - my guess is the entry level is 100k+
    Also I don't think they would offer a sample to see how valuable it is - we didn't get that far in the discussion ;)
     
  10. Consider becoming a member of the industry trade associations you are interested in and read their publications. Find out what's going on in trade shows. Read annual reports. Get economic reports directly from government agencies. With governent reports take quality time in analyzing them and you will glean information that you will not hear on free media. Try to visualize how an industry works and what data is appropiate for monitoring for it. What are the current demographic and social trends and how will various industries be affected? What are regulatory trends for a particular industry or the economy?

    By combining a solid understanding of fundamentals with technical analysis, one may be able to get a sense on whether to focus on trend trading, trading range trading, or a reversal strategy. Being able to gain a perspective of the potential size of a move can improve your R/R significantly.

    As with anything else, work harder than your competition, get paid better than your competition.
     
    #10     May 9, 2018
    jharmon likes this.