Stock Chart Analysis and Artificial Intelligence

Stock Price Correlation Analysis:

Linear correlation is a statistical analysis tool that can help to show if a relationship between 2 parameters exists. The correlation value is called the correlation coefficient and ranges from -1 to 1. A value of 1 means there is perfect correlation. -1 means perfect anti-correlation. And, a value of 0 means no correlation exists between the 2 parameters.

The parameter used in our analysis is the daily percentage change in stock prices for the last 60 days. So a correlation coefficient value of 0.8 means that the daily percentage stock price changes between 2 stocks has shown a strong correlation. This means that over the last 60 days the stock prices changed by about the same percentage change each day. Keep in mind that correlation may or may not be significant. We provide no significance testing here.

Tool #1: Enter a ticker symbol & find it's most highly correlated (or anti-correlated) stocks.

Tool #2: Enter 2 or more ticker symbols & find their correlation values.

Stock Chart Pattern Matching:

Stock Chart Pattern Matcher with Back-Testing Capabilities:

Stock Chart Analysis:
20-day closing lows	20-day closing highs
Closed below lower Bollinger Band	Closed above upper Bollinger Band
9-day SMA crossed below 25-day SMA	Accelerating negative sloped 20-day SMA for last 2 days
Doji candlestick	Accelerating positive sloped 20-day SMA for last 2 days
Closed up more than 5% from yesterday	Volume more than 50% higher than 20-day average volume
Closed down more than 5% from yesterday	Volume less than half of the 20-day average volume
Fast Stochastic (%K) below 5%	MACD showing 12-day EMA more than 3% above the 26-day EMA
Fast Stochastic (%K) above 95%	Close with less than 0.1% change from the close yesterday

List all stocks found in the last 5 days with hits on top technical indicators (sorted by date then by ticker symbol).

List all stocks found in the last 5 days with hits on top technical indicators (sorted by ticker symbol then by date).

Introduction: Stocks have been shown to have non-linear performance. At a deeper level statistical analysis has shown that gains in the stock market do not follow any known distribution such as a normal or 'bell curve' standard distribution. This means that non-parametric statistical analysis must be used to analyze the performance of such stocks. You will notice we use the median instead of the mean to show the average % gains for stocks in our databases. The median is commonly used instead of the mean (simple average many people are used to) when analyzing non-parametric distributions that cannot be transformed into a known distribution. To use median gains for stock analysis makes sense when you consider a few basic characteristics of stocks. First, stocks can hypothetically go up forever. However, they can only go down to zero (a careful consideration for anyone wanting to short a stock). Second, you will find some stocks are much more volatile than others. In other words, not all stocks behave in the same way. Finally, when you consider that some stocks have spiked 50% in a day, then why would we ever want to weight the 50% spike outlier with the rest of the typical data? This is where the median comes in handy since it is the middle value in the data set when sorted from smallest to largest value.
Description of stock analysis service from AiStockCharts.com:
(A) Stock Analysis: When users enter a ticker symbol in our ticker symbol box they will see 2 tables and an interactive chart. The first table lists all the recent hits for this stock on the top indicators. The second table lists the top technical indicators for the stock entered. Click here to learn about our scoring system.
(B) Detailed Stock Analysis: From the stock analysis results page users can click the number of hits found for a particular technical indicator to view the detailed stock analysis page. That page includes a table summarizing the overall results (including $ gains) for the particular indicator when considering all stocks tracked. The page also includes a table and chart summarizing hits for the particular stock and indicator the user is researching. Below the customizable chart is a table listing all technical indicator hits by day for that stock and indicator.
(C) Top Stocks Analysis: When users click on the 'TOP STOCKS' link at the top of AiStockCharts.com they will see 4 tables and an interactive chart. The first table displays the Ai trading log (does not necessarily represent trades placed with real money). The last 10 trades are displayed along with a performance summary. The next 2 tables list todays top long and short stocks with hits on the top technical indicators. The last table lists the historical overall top long and short stocks. All data found in these 3 tables is based on historical data residing in the AiStockCharts.com databases. Databases are updated daily.
Many factors affect the dynamic results found at AiStockCharts.com. Factors include time, S&P 500 index changes, indicator additions, indicators no longer tracked due to insufficient data. Old data is removed since only the last 1350 days of data are tracked. Our Ai programs decide which technical indicators have priority for inclusion in the nightly update.
This Web Site is not an investment advisory service or advisor. We do not tell viewers, or suggest to viewers, what they should buy or sell for themselves. For additional legal disclaimers from AiStockCharts.com visit our TOS (terms of service) page at http://www.aistockcharts.com/tos.htm

Any specific investment or investment service contained or referred to in this web site may not be suitable for all visitors to this site. An investment in stocks may mean investors may lose an amount even greater than their original investment. Anyone wishing to invest or speculate in the stock market should seek his or her own financial or professional advice. AiStockCharts.com is not an investment advisory service and does not recommend the purchase or sale of stocks. There are no licensed financial advisors working at AiStockCharts.com.

HYPOTHETICAL PERFORMANCE RESULTS HAVE MANY INHERENT LIMITATIONS, SOME OF WHICH ARE DESCRIBED BELOW. NO REPRESENTATION IS BEING MADE THAT ANY ACCOUNT WILL OR IS LIKELY TO ACHIEVE PROFITS OR LOSSES SIMILAR TO THOSE SHOWN. IN FACT, THERE ARE FREQUENTLY SHARP DIFFERENCES BETWEEN HYPOTHETICAL PERFORMANCE RESULTS AND THE ACTUAL RESULTS SUBSEQUENTLY ACHIEVED BY ANY PARTICULAR TRADING SYSTEM. ONE OF THE LIMITATIONS OF HYPOTHETICAL PERFORMANCE RESULTS IS THAT THEY ARE GENERALLY PREPARED WITH THE BENEFIT OF HINDSIGHT. IN ADDITION, HYPOTHETICAL TRADING DOES NOT INVOLVE FINANCIAL RISK, AND NO HYPOTHETICAL TRADING RECORD CAN COMPLETELY ACCOUNT FOR THE IMPACT OF FINANCIAL RISK IN ACTUAL TRADING. FOR EXAMPLE, THE ABILITY TO WITHSTAND LOSSES OR TO ADHERE TO A PARTICULAR TRADING PROGRAM IN SPITE OF TRADING LOSSES ARE MATERIAL POINTS WHICH CAN ALSO ADVERSELY AFFECT ACTUAL TRADING RESULTS. THERE ARE NUMEROUS OTHER FACTORS RELATED TO THE MARKETS IN GENERAL OR TO THE IMPLEMENTATION OF ANY SPECIFIC TRADING PROGRAM WHICH CANNOT BE FULLY ACCOUNTED FOR IN THE PREPARATION OF HYPOTHETICAL PERFORMANCE RESULTS AND ALL OF WHICH CAN ADVERSELY AFFECT ACTUAL TRADING RESULTS. THE RISK OF LOSS IN TRADING STOCKS CAN BE SUBSTANTIAL.

Stock trading is speculative and a substantial risk of loss exists. Past performance is not necessarily indicative of future results.