algorithmic trading with i know first introduction packet
DESCRIPTION
Contents - About I Know First - How To Read The Prediction • Signal • Predictability Indicator - Sample Top 10 Algorithmic Forecast & Corresponding Returns - Example Analysis of Tesla (TSLA) By An I Know First - Research Analyst How To Recognize Overall Market Trends - Algorithmic Trading StrategiesTRANSCRIPT
Algorithmic Trading With
Introduction Packet
Contents
About I Know First
How To Read The Prediction
• Signal
• Predictability Indicator
Sample Top 10 Algorithmic Forecast & Corresponding Returns
Example Analysis of Tesla (TSLA) By An I Know First Research Analyst
How To Recognize Overall Market Trends
Algorithmic Trading Strategies
About I Know First
I Know First is a financial services start-up that utilizes an advanced self-
learning algorithm to analyze, model and predict the stock market. Co-Founder
Dr. Lipa Roitman, a scientist with over 20 years of experience created the market
prediction system. The algorithm is based on artificial intelligence, machine
learning and incorporates elements of artificial neural networks as well as
genetic algorithms to model and predict the flow of money between 1,400
markets from 3-days to a year: stocks, ETF's, world indices, gold, currencies,
interest rates, and commodities.
It separates the predictable part from stochastic (random) noise and then
creates a model that projects the future trajectory of the given market in the
multi-dimensional space of other markets. The algorithm outputs a predicted
trend as a number, which in turn, is used by traders to identify when to enter
and exit the market. While forecasts can be used for intra-day trading, the
predictability tends to become stronger over longer time-horizons such as the
1-month, 3-month and 1-year forecasts.
How To Read a Prediction
In each algorithmic forecast, there is the signal and the predictability
indicator. The signal is the number in the middle of the box (flush right). The
predictability is the number at the bottom of the box. At the top, a specific
asset is identified. This format is consistent whether you are receiving the Top 10
Stock Predictions + S&P Forecast or the Top 10 Commodities Forecast or any
other I Know First prediction for that matter.
This algorithmic forecast for Tesla was made on May 12th 2014. Within the
predicted time horizon (time frame), TSLA shares gained 4.59% in accordance
with the algorithmic forecast. Before making any trading decisions, consult the
latest forecast as the algorithm constantly updates predictions daily. While the
algorithm can be used for intra-day trading the predictability tends to become
stronger with forecasts over longer time-horizons such as the 1-month, 3-month
and 1-year forecasts.
Signal: This indicator represents the predicted movement direction/trend; not a
percentage or specific target price. The signal strength indicates how much the
current price deviates from what the system considers an equilibrium or "fair"
price.
Analogy with a spring: The signal strength is how much the spring is stretched
The higher the tension the more it will move when the spring is released.
The signal strength is the absolute value of the current prediction of the system.
The signal can have a positive (predicted increase), or negative (predicted
decline) indication. The heat map is arranged according to the signal strength
with strongest up signals at the top, while down signals are at the bottom. The
table colors are indicative of the signal. Green corresponds to the positive signal
and red indicates a negative signal. A deeper color means a stronger signal and
a lighter color equals a weaker signal.
Predictability: This measures the importance of the signal. The predictability is
the historical correlation between the prediction and the actual market
movement for that particular market. For each asset this indicator is recalculated
daily. Theoretically the predictability ranges from minus one to plus one. The
higher this number is the more predictable the particular asset is. If you compare
predictability for different time ranges, you'll find that the longer time ranges
have higher predictability. This means that longer-range signals are more
important and tend to be more accurate.
* Stocks with the strongest signal and largest predictability are preferable.
Signal and Predictability are independent indicators. While the signal
gives the direction and the relative "scale" of the predicted move, the
predictability indicator is related to the probability of that prediction to realize,
which is based on the past performance of the corresponding predictor. Both of
the parameters are important. The higher both are the better. It is
recommended to consider both the signal strength and predictability.
Sample Top 10 Algorithmic Forecast & Corresponding Returns
Below is a typical Top 10 Stocks Picks & S&P 500 Forecast in the 1-year
time horizon with the correlating returns in a table to the right. A “✓”denotes a
correct prediction while an “x” conveys that the stock did not move in the
forecasted direction.
There are multiple strategies that can be utilized with algorithmic
forecasts that will help mitigate risk and enhance returns. All of which are
recommended to be coupled with traditional forms of analysis. Forecasts can be
customized to fit certain criteria such as being large cap, have a dividend, low
volatility or a specific industry that best suits any investment strategy required.
Example Analysis of Tesla (TSLA) By An I Know First Research Analyst
First and foremost, for any trading decisions use the most recent forecast.
In general, the longer time range forecasts are more predictable than the
shorter ones and they should be used to identify the main market trends. We
recommend that for the first month of your subscription that you watch the
system, learn it and become familiar with it before actually making trading
decisions on accord with the daily forecasts.
The first appearance of a stock in the top list does not mean you should
buy it at any price that same day. Instead, put it in a watch list, unless you are
getting it at a significant discount. We advise that you wait three to five days to
get it at the better price. Try to get into the market at a discount of at least three
percent when the market goes against the prediction intraday or in the next few
days after the first appearance of the signal. Look for trends such as an
increasing signal or
predictability to gain more
confidence in the prediction.
To the left are the 1-month
and 3-month forecasts of
Tesla from May 7th – May 9th
2014. The algorithm indicates
that shares will increase in
value over these time
horizons. These forecasts
display an increasingly bullish
forecast for Tesla. In the 3-
month time horizon, Tesla has
6.41, 8.32 & 28.55 signals for May 7th, 8th and 9th, respectively. As each
forecast is color-coded, the algorithm indicates increased strength of the
predicted movement in this forecast with a deeper green. Deeper greens and
reds indicate more aggressive movement in the stock price and are directly
related to the strength of the signal. However the predictability is not very
strong in either the 1-month or the 3-month time horizon, meaning the
algorithm is not very confident in this forecast. Algorithmic forecasts are
intended to be utilized in conjunction with traditional forms of analysis in order
to reduce risk and optimize returns.
How To Recognize Overall Market Trends
Be sure to recognize the general color of the heat map as well as
consider the forecasts for major indexes like the S&P or Dow Jones to get an
overall picture of the market trend. We advise not to trade against the general
market trend. Another tactic is when you look at specific stocks like Citigroup
(C), is to review the specific industry forecasts such as the KBW Bank Index (BKX)
as well to develop a better analysis. To get a strong indication of market
volatility, the Volatility Index (VIX) forecast is an excellent indicator. If an asset
you purchased is no longer in the Top 5, 10, 20 or 40 you can easily receive a
customized forecast to continue tracking the asset.
While reading your Top Stocks forecast, there are three specific indicators
of how the general market will perform. The first is simply recognizing the
forecast for the S&P 500. The second indicator in your Top Stocks forecast is the
overall color of the entire forecast. When the entire forecast is primarily green,
this should give more faith in the algorithmic predictions as well as express the
general forecasted market environment. The final indicator is the bar across the
top of the forecast, under the date.
When you hover your mouse curser over each cell in this bar, it will show
useful information such as how many assets have bullish signals. In this
example, 37%, 34%, and 23% assets have bullish signals for the 1-month, 3-
month, and 1-year time horizons, respectively. The other boxes give information
such as the average signal, the previous percentage of stocks with a bullish
signal, the average predictability and other useful information that will reveal the
forecasted market environment.
Algorithmic Trading Strategies
Strategy 1: Identify New Opportunities and Double-Check Your Analysis
As you do your own analysis of companies, you can compare your
assessment with that particular assets forecast. On the other hand, you can do
the exact opposite by recognizing new market opportunities and then doing
your own analysis of the assets that have strong signals and predictabilities. This
strategy is a great way to check your analysis as well as recognize opportunities
you would have otherwise missed. This is an excellent way to mitigate risk and
optimize returns especially if your own analysis agrees with the forecast. If you
specialize in a particular industry we recommend getting a forecast that identifies
the best and worst companies in that industry such as our Best Tech Stocks
forecast
Strategy 2: Buy All Assets In The Forecast Of Equal Weights
Another popular approach is to purchase all the assets of the forecast in
equal weights. This strategy will help diversify your portfolio, ultimately reducing
risk and augmenting returns. The I Know First Average Return reflects the return
an investor will receive implementing this strategy. While not every
recommended asset will follow the predicted movement, those that do not
usually will not deviate tremendously and investors will benefit from the assets
that do follow the prediction. The I Know First Live Portfolio is a great example of
how this strategy has proven effective. The portfolio is based on the average
return from the Top 10 Stocks + S&P 500 forecast in the 1-month time-horizon
purchased on the first of each month, representing a buy and hold strategy. The
portfolio returned 60.66% in 12 months beating the S&P 500 by over 30% in 2013.
Strategy 3: Buy Only Stocks With A Predictability Of .4 Or Higher
This strategy is straightforward and very dependent on the predictability
indicator. This indicator, which is unique to I Know First: Daily Market Forecast’s
algorithm is the historical correlation between prediction and the actual
movement of that particular asset. In other words, this measurement indicates
how often the algorithm has been correct in the past. Generally a predictability
of .2 and higher is considered very good but a predictability of .4 and higher is
excellent. This strategy is somewhat limited in scope but can be a very reliable
tactic.
Strategy 4: Buy Stocks That Have A Strong Signal In Each Time Horizon
Our fourth strategy is based on recognizing assets to reappear in each
time horizon. When you see the same asset in your forecast appear in the 1-
month, 3-month, and 1-year time horizons, this is good sign. The next step is to
analyze the signal and predictability. You should look for a consistently strong
signal and predictability in each time horizon. Generally you will see the
predictability indicator increase in larger time-horizons, and this is sometimes the
case with the signal as well.
Strategy 5: Multiply the Signal And The Predictability Indicator Together
This approach requires some basic math skills, specifically multiplication.
When you multiply the signal and predictability, you basically create your own
new indicator. This will allow you to easily compare the different assets in your
forecast. The same rule applies, as the larger numbers will denote a stronger
forecast.
Email us with any questions that you may have. We would be happy to help.
Customized forecasts are available, including adding specifics such as large cap
or small cap stocks, additional tickers, different assets including commodities,
currencies, ETFs, world indices or any of the + 1,400 assets.