[Last Call] Learn about multicloud storage options and how to improve your company's cloud strategy. Register Now


Interpreting Curves - Rates of Change etc...

Posted on 2007-11-20
Medium Priority
Last Modified: 2008-04-04

i apologise up front for the vagueness of this question!

i collect various data types(primarily odds from betting exchanges) and graph this data which all looks very pretty.
from the graphs i can visually identify trends etc... such as sudden/longer term movements
The problem i have is that i now need to develop an application that can interpret the graph and automatically identify the trends that are occurring.
I've looked into areas such as rates of change(slopes), differential calculus, moving averages etc... all in an attempt to find a way of defining the graph/curve at certain points and over a specified period.
admittedly this is not an area that i have any great experience in. so i find myself guessing a lot and am not sure where to focus in on to make any progress.

so the question i have is, as a general rule what areas should be focussed on when attempting to define a curve.
i realise that the answer to this question is dependant on the data being analysed, but i'm really looking for a starting point.
for example, am i better concentrating on rates of change over ceratin periods. what does finding the derivative at various points really tell me? a

any and all suggestions are welcome!
again, sorry about being so vague!

Question by:Fatlog
Welcome to Experts Exchange

Add your voice to the tech community where 5M+ people just like you are talking about what matters.

  • Help others & share knowledge
  • Earn cash & points
  • Learn & ask questions
LVL 18

Expert Comment

ID: 20320430
LVL 22

Expert Comment

ID: 20320580
What you're talking about sounds a lot like Technical Analysis, which is the term for a general art of analyzing stocks from chart information.  That would make a good starting point.  http://en.wikipedia.org/wiki/Technical_analysis
LVL 27

Expert Comment

ID: 20321816
moving averages has a long history of use in predicting sunspot activity.
If you are looking for unusual betting activity, you might calculate the dirivitive of your curve and program an alert to sound when it changes by a predetermined amount.
Concerto Cloud for Software Providers & ISVs

Can Concerto Cloud Services help you focus on evolving your application offerings, while delivering the best cloud experience to your customers? From DevOps to revenue models and customer support, the answer is yes!

Learn how Concerto can help you.


Accepted Solution

mandelia earned 800 total points
ID: 20326895
<<<as a general rule what areas should be focussed on when attempting to define a curve. >>

Derivatives.  Derivatives of a curve tell you a lot about the tind of curve.
The more deep you go. Degree of derivatives better you can mathematically define your curves

Expert Comment

ID: 20413592
I agree with every thing written here and must say it similar to technical analyze of stock market and the same rules will work in your case. learn a little bit on the subject and get to know terms like signal, entry point, exit point, strategies and find the eqvilent in your field.

Mandelia - I think derivatives will not work there as it a statistical data that unlike "regular" function (of any order) would  work only on a given data segment without prediction of out-scope segments.

Expert Comment

ID: 20417424
Hilay- I suggested derivatives because the question specifically said "Rate of Change".
Even if the data i collected samples like in a stock market. derivatives is what we use to analyse data.
The only difference is we segment our data. derivatives, local maximas and minimas, support and rate of growth are all some of the most common form of derivatives that a stock analyst looks at.
In stock analysis, we first need to smoothen data ignoring spikes and then analyse it. Even conditioning of data differs from one analysis to other

Author Comment

ID: 20418455

thanks for all the comments!!! keep them coming.
i am very new to this and am trying to keep my head above the water at the moment so all comments help.
the one thing i need to be able to achieve is some way of automating the analysis of data so that a person isn't involved.

on another note, the markets i am looking at are odds markets that generally start every morning and finish sometime during the day. in general what would be a good time frame to analyse the data. seconds, minutes, hours?
also, these markets tend to become very volatile close to the market close time when large volumes of money are being fed into the market. is this type of sudden movement even predictable?

i appreciate that you may not know the markets in question and therefore are unable to give a concrete opinion. but i'm wondering if some of the behaviours that i see in these markets are common in other areas/markets. does volume in general dictate movement?

thanks again

Assisted Solution

mandelia earned 800 total points
ID: 20418794
Fatlog : Are you trying to develop such a analytical tool or you are open to buying these things.

If you just want a idea of what kind of analysis can be done you can look at matured analytical tools used for stock market analysis or the one used by google Analytics. The number of ways a data can be analysed depends on what you want to get from it. Rest everything can be automated.

Just an example : Farcs, Fanlines, Cyclelines, Parellels are few studies that can be done. These can be done on both volumes, odds, % move or any other dimention of the market. All these can be programmed to have programatically. But the harder question is to know what you want to see

Featured Post

Free Tool: ZipGrep

ZipGrep is a utility that can list and search zip (.war, .ear, .jar, etc) archives for text patterns, without the need to extract the archive's contents.

One of a set of tools we're offering as a way to say thank you for being a part of the community.

Question has a verified solution.

If you are experiencing a similar issue, please ask a related question

Introduction On a scale of 1 to 10, how would you rate our Product? Many of us have answered that question time and time again. But only a few of us have had the pleasure of receiving a stack of the filled out surveys and being asked to do somethi…
This article seeks to propel the full implementation of geothermal power plants in Mexico as a renewable energy source.
This is a video describing the growing solar energy use in Utah. This is a topic that greatly interests me and so I decided to produce a video about it.
Although Jacob Bernoulli (1654-1705) has been credited as the creator of "Binomial Distribution Table", Gottfried Leibniz (1646-1716) did his dissertation on the subject in 1666; Leibniz you may recall is the co-inventor of "Calculus" and beat Isaac…

650 members asked questions and received personalized solutions in the past 7 days.

Join the community of 500,000 technology professionals and ask your questions.

Join & Ask a Question