Last Month Data, All tickers Included:
Since the 6 september from the 06 october, Gambiste retrieved 2 669 899 tweets. We created a simple barchart to show the Most Tweeted Tickers during this period.
Since the 6 september from the 06 october, Gambiste retrieved 2 669 899 tweets. We created a simple barchart to show the Most Tweeted Tickers during this period.
Stock is a popular topic in Twitter. The number of tweets concerning a stock varies over days, and sometimes exhibits a signiﬁcant spike. In this paper, we investigate Twitter volume spikes related to S&P 500 stocks, and whether they are useful for stock trading. Authors develop a strategy that combines the Bayesian classiﬁer and a stock bottom picking method, and demonstrate that it can achieve signiﬁcant gain in a short amount of time. Simulation over a half year’s stock market data indicates that it achieves on average 8.6% gain in 27 trading days and 15.0% gain in 55 trading days. Statistical tests show that the gain is statistically signiﬁcant.
At Gambiste, we can provide our tweet volume data. The last month tweet volume data is currently free of charges for Alternative currencies here.
Autors studied other related works, indeed several studies use Twitter to predict stock market. A recent study finds that specific public mood states in Twitter are significantly correlated with the Dow Jones Industrial Average (DJIA), and thus can be used to forecast the direction of DJIA changes. Another study finds that emotional tweet percentage is correlated with DJIA, NASDAQ and S&P 500. Later on, the study finds that Twitter sentiment indicator and the number of tweets that mention financial terms in the previous 1-2 days can be used to predict the daily market return.
The authors investigate whether the number of tweets for a stock spikes around the earnings dates. Suppose that a company’s earnings date is day t. An analysis takes place on whether the number of tweets on the company’s stock spikes around t, in particular, on days t−1, t and t + 1. In the data collection period, there are 509 earnings days for the stocks that were considered. They found 79.2% of them are surrounded by a Twitter volume spike, conﬁrming authors’ thoughts that people indeed tweet more about a stock around its earnings dates.
Time difference(in days) from an earnings day to the closest day that has a Twitter volume spike. A negative value corresponds to the time difference to the closest Twitter volume spike in the past.
Twitter volume spikes close to earnings days are likely due to the earnings days themselves. Since earnings days are public information that people know beforehand, these Twitter volume spikes are no surprises. These spikes cannot be used in building a trading strategy as the price reflects them beforehand. Thus, the authors needed a way to determine if a certain spike was expected or not. Option implied volatility can be used as an indicator to determine whether a Twitter volume spike is expected or not, whether it is related to a scheduled event.
Assume that for a stock, a Twitter volume spike happens on day t. In this figure, average daily implied volatility is plotted for both short-term options, i.e., those that will expire in 30 days after t, and longer-term options, i.e., those that will expire in 30 to 60 days after t. For short-term options, it can indeed be seen that the daily average implied volatility increases before t and decreases after t. For longer-term options, the trend is not clear. It was found out that 37.3% of the Twitter volume spikes are . Note that this percentage is a very conservative estimate and serves more like a lower bound, showing that a fair share of spikes are expected.
The authors now investigate potential causes of Twitter volume spikes. Speciﬁcally, they consider the following ﬁve factors:
1. Stock breakout point,
2. Intraday price change rate,
3. Interday price change rate,
4. Earnings day, and
5. Stock option implied volatility.
Then, the authors calculate the correlation of each of these ﬁve factors with Twitter volume spikes.
The correlation analysis resulted in the following figure:
On the y axis we can see the CDF (cumulative distribution function) of the correlations between Twitter volume spikes and each of the ﬁve factors over all the stocks. Twitter volume spike has the strongest correlation with earnings days (with median of 0.37), which conﬁrms our earlier result that a signiﬁcant fraction of Twitter volume spikes occurs around earnings days. The correlation between Twitter volume spike and implied volatility has a median value of 0.14, much stronger than the correlation with the rest of the factors.
Two trading strategies were developed, both using Twitter volume spikes as trading signals. For comparison, a baseline strategy that purchases a stock on a random day, and a strategy that uses trading volume spikes are considered.
First strategy was based solely on Bayesian classiﬁer.
Classifier’s training factor was the probability that buying the stock can lead to proﬁt after a number of days was calculated, and the stock was only bought when the probability was sufﬁciently large (above 0.7).
To evaluate the strategy, the data from February 21, 2012 to October 19, 2012 was used as training data, and the data from October 20, 2012 to March 31, 2013 was used as test data. This results in 573 Twitter volume spikes in the training set, and 672 Twitter volume spikes in the test set.
Implied volatility factor was excluded from testing and training because it requires using option data and hence does not provide a fair comparison with other strategies.
The results of the above simple strategy are encouraging, indicating that Twitter volume spikes are indeed useful in stock trading. On the other hand, the strategy does not consider the trend of a stock. For instance, it may buy a stock when the price of the stock is increasing, which may not lead to proﬁt. So, the authors propose an enchanced strategy that takes trends into consideration.
The authors combine the Twitter volume spike strategy with a Zigzag based algorithm (based on ZigZag indicator), used to identify turning points for a given movement rate, λ, which is deﬁned as the minimum price difference ratio between two adjacent turning points.
The stock price turning point identiﬁcation algorithm for a given λ is described as follows:
(1) Start the search from the ﬁrst point in the dataset. Search forward until a potential turning point is found, i.e., one of the two conditions holds: (i) the price increases by at least λ from the start point, or (ii) the price decreases by at least λ from the start point. Continue the search.
(a) If condition (i) holds (i.e., the price moves upward), update the potential turning point when ﬁnding a point that is larger than the previous potential turning point. When ﬁnding a point that drops at least λ compared to the current potential turning point, set the current potential turning point to be a downward turning point.
(b) If condition (ii) holds (i.e., the price moves downward), update the potential turning point when ﬁnding a point that is smaller than the previous potential turning point. Set the current potential turning point to be an upward turning point.
(2) Start to search from the turning point. If the turning point is a upward turning point, go to Step (1a). If the turning point is a downward turning point, go to Step (1b). Repeat until the end of the data set.
For the stock, the top ﬁgure shows the price chart; the bottom ﬁgure shows the tweets ratio, i.e., the number of tweets on a day over the average number of tweets in the past 70 days, over time. A day with tweets ratio above K has a Twitter volume spike.
Thus, a factor of the price being near the upward turning point of the ZigZag is added to the strategy.
The authors conﬁrm that there is indeed strong evidence that the proﬁt is positive, and the enhanced strategy outperforms the random strategy as well as the strategy that uses stock trading volume spikes.
This figure plots the fraction of the winning trades using the enhanced strategy. We can observe that signiﬁcant fraction of the trades lead to proﬁt. For instance, when using intraday and interday price change rates, as much as 89.3% of the trades lead to proﬁt in 29 days.
Simulation over a half year’s stock market data demonstrates that both strategies lead to substantial proﬁts, and the enhanced strategy signiﬁcantly outperforms the basic strategy and a bottom picking method that uses trading volume spikes, which proves that using Twitter volume spikes in trading can indeed provide a statistical/trading edge and should be employed by the traders.
Retrieve last month tweet volume data on our website free of charge. We can also provide on demand the tweet volume data on alternative currencies and stocks since early 2015.
Gambiste provides a Tweet Volume on Stocks and Crypto Currencies designed to help investor gauge the market appeal on symbols. Social media is the new data type that you must integrate in your trading strategy to grasp all opportunities. We provide an overview of our processes in this article.
The researchers of the University of Connecticut showed that Twitter data can improve your trading strategies. They published the study “Twitter volume spikes and stock options pricing” in the journal Computer Communications.It reveals how spikes in the number of tweets about a company can be used to design a profitable stock options trading strategy.
“Our results show that social media is a powerful tool to help understand the behavior of stock options, and further assist the trading of these valuable, but complex investment vehicles,”said Bing Wang, associate professor of computer science and engineering, one of three authors on the paper.
At Gambiste, we worked since 2015 to deliver the most qualitative and advanced Tweet Volume on securities.
Traditional financial institutions pay thousands of people to read and prepare investment notes and advices, that the reasearch business. Mac Kinsey estimates that the top-10 sell-side banks currently spend $4 billion on research annually for a cash equity research headcount of 3900 in 2011. Gambiste thinks that this industry will face big challenges, not only regulatory but also technological.
The volume of social media information is enormous. There is more than 500 million tweets posted on Twitter per day. It makes tapping into the potential value and deriving insight a challenge. That’s also a huge opportunity. It’s why the process is hidden underneath.
So for traders and investors looking for an edge, the core challenge in mining social media remains. That is, how can the truly valuable information — which represents a small percentage of the overall feed — be extracted and presented to the trader ?
We developed our social indicators using data from Twitter. The data is retrieved automatically. Our application extracts relevant tweets. We developed our own spam filters to remove abusive Tweets. So at first, we apply machine learning classifiers to keep the ‘good’ tweets.
For example, we identified this tweet on the symbol $BTC as spam. This is a classical tweet. @techCrypto asks others to sign on his website. To reach people, the spammer add the Tickers $BTC, $LBC, $LKK. When a user searches for one of these Tickers in the search tool of twitter, it will display this tweet with bad content.
We discard a lot of messages. It represents 70% to 90% of the messages that we retrieved. We remove theses ‘spam’ Tweets from the Gambiste Tweet Volume and we keep the good ones.
We don’t stop here. Each user does not have the same weight. Depending of your reputation, we will not account the same score to a given tweet. It depends of the engagement that a given user can generate based on multiple factors. Your reputation score depends of your number of followers, tweets, likes received…
In fact, Gambiste does not calculate the reputation score. That’s not our business. For this matter, we use a leading reputation indicator. Gambiste discounts the tweet created by user with a low reputation.
Similarly, we also discount the tweet with several Cashtags (e.g. $AMZN, $GOOG, $HALO). Spammers create tweet with many symbols to attract views. If we took into account these messages, this would totally disrupt our count. The application manages these tweets by splitting their points betweet each ticker. The application divides the global score of the tweet below by the number of symbols. Such as the tweet below, there is 7 symbols so we divide by 7. We then add the fractioned score to the current Ticker score [$BTC actual score + 1/7 of the Gambiste tweet score].
— Gambiste (@GambisteFinance) October 3, 2017
To recapitulate, Gambiste has a tree steps process:
to provide an accurate picture of the tweet volume on a given stock symbol and Gambiste does that live, continuously.
We developed two distinct streams: one for the Alternative Currencies and one for American Securities. We published recently a research screen to browse into the tweet volumes calculated by Gambiste on the Alternative Currencies. Crypto currencies are chatted a lot on Social Media. Satoshi Nakamoto released the Bitcoin as a decentralized digital currency in 2009; tree years after the creation of Twitter. Crypto fans are some native users of social media.
Hedge Funds and Wealth Management Brokerage Firms implements social media stock data into their overall trading strategies. They capitalize on this lucrative insight since years. And you know what ? Their results have been staggering and they don’t want to share it. Individual investors also need access to this high level structured information in order to compete with professionals. This is exactly what Gambiste provides today .
To conclude, we improve our algorithms every day to provide to our end users actionable data sets that can be incorporated into existing algorithm. We want to dramatically improve your trading performance and your stocks discovery process.
As Finance Professionals, we were crawling tickers in Twitter to retrieve the best info of the day.
We searched symbol after symbol if something was going on on a stock, even more during the earnings season. This can be exhausting, so many tickers and so many bots spamming around. But we continued to do it cause Twitter provides a nice way to speak directly to other investors, share thoughts and see what’s going on in the market.
One day, we said, well maybe should we use the twitter api to retrieve the tweets, simply compute the data (maybe with one or two machine learning tricks) and then just browse between the best ticker symbols of the day smoothly, that sounds easy, no ?
Well that was two years ago, when we started Gambiste Finance. That’s an exciting journey with many challenges and we are proud to continue to deliver new releases to our customers and our free users of the Gambiste Reports.
At Gambiste Finance, we are committed to explore and share our products to a large audience. We focus on the creation of comprehensive social media indicator designed to better trade stocks and other types of financial instruments. These indicators must help to better undersand the impacts of social media discussions on stocks prices, trading volume, trader attentions.
Our products use the last researches done in the the field of Machine Learning, Finance and IT, nonetheless we aim to deliver simple and actionable tools for trading and to better understand the information in the social media era.
We will integrate virtual currencies in our platform. We heard lately in main stream media that $BTC and $BCH (Bitcoin Cash) could propel higher AMD or NVidia stocks. Nowadays, altcoins are just the new normal and so they deserve their own Gambiste reports.
We recently delivered our new report, the Alternative Currencies Top 10 weighted by market capitalization. The Alt currency Top 10 is published 4 times a day on our website. In this report, Gambiste Finance will highlight the most tweeted crypto currencies by coin capitalization . As you will see, the bitcoin is not always in the first position, some other coins are also popular on the social network.
Gambiste delivered a new release with some algorithms updates yesterday. There’re basically two new functionalities. With these upgrades, our reports are now more user friendly and more than ever focused on the traders’ needs.
Indeed, the Gambiste scores range now from 0 to 100. The more a company is tweeted, the more its score will be close to 100 and inversely. So, now Gambiste Score are normalized, daily normalized for our daily reports but other time spans are possible. The main idea here is to compare one stock to another.
A tweet volume is not a price quoted in USD or EUR. It only has value when it’s put into context with other comparable results. It sounds 100% meaningful to us but we definitely remain open to the feedbacks of our beloved early users.
A company with a bigger market capitalization has usually more employees, a bigger marketing budget, better products or at least a wider range of products. That leads to more tweets on the company. We reduce this factor by weighting the daily volume of tweets by the market capitalization of the stock. We can really discover some interesting things discrepancies between Tweet volumes when they are properly weighted.
We will from now on publish 4 new reports:
The stocks with big capitalization are valued above 10 billions. Mid caps are valued between 10 billions and 2 billions then Small caps range between 2 billions and 300 millions. Finally the Micro caps weight between 300 millions and 50 millions. Gambiste does not produce yet reports with nano caps, nonetheless that was one of the most tweeted stocks lately. Indeed with the sector of maritime transports going through a crisis, their mcaps have fallen drastically. We saw symbols like $DRYS or $TOPS on top of the global ranking for weeks.
So one of our priorities is to produce a dedicated report for Alternative currencies regrouping the Cashtag used by Twitter users to speak about Virtual currencies.
The next priority is to better weight the message with several cashtags. These messages could be underweight, theirs points split between their different symbols. It would immediately reduce the impact of message created by bots with several cashtags in it.
We are proud to deliver today a unique ranking. Gambiste Financials releases today, the most tweeted stock by market capitalization. This article describes why it matters and how we built this new service.
Our goal is to develop a valuable indicator of stock attractiveness. We think that stock opinions shared through social media are valuable. This subject is discussed by recent papers published in academic research journals. What if we were the first to aggregate this content in one indicator ? An indicator designed to rate the actual stock attractiveness. This is what we provide today,. The first public indicator mixing traditional signals (like stock quotes and actual market capitalization) and social media data.
We worked hard at Gambiste to deliver swiftly this new ranking. It takes into account the tweet volume scores calculated by our algorithms for stocks listed on the NASDAQ. We also retrieve from the NASDAQ the official market capitalization by stock. In this new list, we provide the stock with the best tweet volume for their market capitalizations. In addition, our applications deliver several times by day a TOP 10 reports on Twitter. Follow our account @GambisteFinance on Twitter.
Why ? The aim is to compare the Gambist Financials Tweet Score on a comparable scale.
If we speak about the AmazonTweet Score or the Halozyme Therapeutics tweet score. $AMZN is one of the biggest company in the world that you probably know. At first this was only an online book shop . $HALO is a pharmaceutical company specializing in oncology with a 1 billion market capitalization. $AMZN is worth hundreds of billions. $HALO is worth 2 billions. So our algorithms scale the number of tweets observerd on a company by its market capitalization.
We firmly believe that a company with a bigger market capitalization draws more attention, in overall. This attention leads to more tweets thus we normalized our tweet volume score by the Market Capitalization to mitigate its impact. We update this market capitalization every day with NASDAQ data to reflect accurate numbers.
Now, we highlight the fact that the Tweet volume score is only an evaluation of the social media activity for a given symbol. This indicator can deviate somehow of the real volume on Twitter at the present time (e.g. if there is a spike of activity on the social network). This indicator takes all tweets including to a stock symbol ($MOSY, $TOPS). This includes the tweets produced by bots.
We are pleased to be the first company to deliver the first Tweet volume indicator weighted by Market Capitalization. This indicator is so useful to detect events realized or in construction and discover new trends, new gems. We hope that you will like it as we do. In a near future, we will provide to our users new tools to measure the correlation between the market capitalization size and the social media volume score using new proprietary algorithms.