# Share Market Sectoral Indices Movement Forecast with Lagged Correlation and Association Rule Mining

## Summary (3 min read)

### 1 Introduction

- The basic idea behind technical analy- sis is that current stock price of a company incorporates impacts and effects of eco- nomic, financial, political and psychological factors.
- In any Stock market listed companies are categorized into different sectors depending on the business domain the company belongs to.
- In the next sub section the authors briefly discuss about Indian share market as well as sectoral indices that are considered in this case study.

### An Overview of Indian Share Market

- Two most important stock exchanges in India are BSE and NSE.
- The Bombay Stock Exchange (BSE) is one of the oldest stock exchanges in India and one of the top stock exchanges globally with respect to number of listed companies and market capitalization.
- These are some of the largest and most actively traded stocks, hence it is con- sidered as representative of various industrial sectors of the Indian economy.
- It is published since 1st January 1986 and regarded as the pulse of the domestic stock markets in India [9].
- The NIFTY 50 index is n tion l stock exch nge of Indi ‘s benchmark stock market index for Indian equity market [10].

### Statistical Correlation

- Let Xt and Yt are two given time series closing prices for N days.
- Cross correlation between them is defined as- Where x , and Y ; Sx , Sy being the sample standard deviations of series X and Y.
- Any positive r values between 0 and +1 indicates that the relationship between x and y variables are such that with increase in values of X, Y value also increases.
- R value closer to 0 signifies that there is no linear correlation or a very weak correlation, also known as No correlation.
- Gener lly with noisy data less threshold values are considered.

### Association Rule Mining

- Data mining, an important part of knowledge discovery in databases (KDD) pro- cess employs many different techniques for knowledge discovery and prediction such as classification, clustering, sequential pattern mining, association rule mining and analysis.
- From the frequent item-sets a set of strong rules are calculated.
- Not all frequent item- sets are considered as strong, only those with a minimum support and confidence are considered for the next step.
- It indicates if people are buying bread and sugar then they may also buy butter.

### 2 Related Study

- In another study work authors investigated stock index comovement between two different countries namely Taiwan and Hong Kong using association rules and cluster analysis [6].
- Authors in [16] has analyzed correlation between stock price fluctuation, gold price and US dollar price along with association rule induction methods amongst different stocks of same sector.
- In another work authors proposed and evaluated a stock price prediction based recommender system [18] that used historical stock prices as input to the system and applied regression trees for dimensionality reduction and Self Organizing Maps (SOM) for clustering.
- The main objective of this research work is to measure the association between sectors pair-wise instead of specific stock.

### Research Framework

- The research framework of this study is shown in Fig.
- It involves collecting in- dex values of 6 industrial sectors from NSE.
- Each trading days closing prices are used as the raw input data for their analysis.
- Initial time series plotting of sectoral indices of selected sectors gives a basic graphical visualization of the raw data about their co-movement pattern.
- Raw dataset is then processed into proper format to be used in association rule mining and for correlation analysis.

### Correlation Analysis

- The authors data set consists of day wise closing prices of 6 different sectoral indices of 2015.
- The authors then calculated pairwise correlation for all the possible pair of sectors with a lag of 0 day to 5 days.
- A delay of 0 day means same day correlation between the two sectoral indices.
- Microsoft excel spreadsheet based statistical tools has been used to derive the re- sults shown in table 1 and Fig.
- In this study a correlation value of r >=0.8 has been considered as good correlation nd correl tion v lue of r<=0.5 h s been neglected s ‗the authors k or no correl tion‘.

### Data Preprocessing and Encoding

- Whole dataset contains such sectoral index closing prices of 6 sectors.
- For their experiments the authors have considered ∆t =0.2 as it gives good results.
- Step 1: change in index values are calculated for each sector as follows: ∆pi = pi+1 -pi Step 2: Different sectoral index values has different base and movement amount in absolute values so to normalize all sectors the authors consider percentage change.
- Ci value may be positive or negative depending on the price movement of the sec- toral index.
- Here vi becomes +1 if change is in positive direction i.e. sectoral index moves upwards.

### Rank the Generated Association Rules

- Rank all the derived association rules as per there support and confidence value.
- Value of K depends on the investors risk profile and preferences.

### 4 Results and Analysis

- The authors have used open source java based frequent pattern mining library SPMF [7] for deriving association rules with apriori and suitably modified to incorporate other required changes.
- Fig. 2 shows the initial time series plotting of different sectors where co-movement patterns can be visually seen.
- Different correlation values are plotted against delay in Fig. 3 to show the positive, negative as well as no-correlation between different sectors with varying delays.
- Finally table 2 shows the top 15 association rules that re mined using the bove mentioned method nd r nked s per rules‘ support nd confidence measure.
- IT and pharma index also shows similar pattern.

Did you find this useful? Give us your feedback

##### Citations

37 citations

### Cites methods from "Share Market Sectoral Indices Movem..."

...in [5] has used RNN-LSTM model on NIFTY-50 stocks with 4 features (high/close/open/low price of each day)....

[...]

8 citations

6 citations

6 citations

##### References

15,645 citations

3,198 citations

### "Share Market Sectoral Indices Movem..." refers background in this paper

...Agrawal [13] first introduced association rules for frequent pattern mining among items in large transaction dataset....

[...]

2,149 citations

### "Share Market Sectoral Indices Movem..." refers methods in this paper

...We adapt the association rule mining using Apriori from [11] and used lift value[19] as a measure of interest of the mined rules....

[...]

181 citations

### "Share Market Sectoral Indices Movem..." refers background or methods in this paper

...along with priceto-earnings ratio, dividend yield, profit margin , return on investment etc.[2,3,12,15]....

[...]

...Several researches have been done over the period on predicting future stock price or price movement direction (upward or downward) along with trend analysis based on mainly different statistical modeling [3,4,6,7,8,14,15]....

[...]

...have been proposed and tested with mixed success[1,2,3,15]....

[...]

...It is defined for rule R as the ratio of the number of occurrence of R, given all occurrences of all rules [3]....

[...]

133 citations

##### Related Papers (5)

##### Frequently Asked Questions (13)

###### Q1. What are the contributions in "Share market sectoral indices movement forecast with lagged correlation and association rule mining" ?

This paper analyses the correlation between two different sectoral indices ( e. g. between Automobile sector index and between Metal sector index, between Bank sector index and IT sectoral index etc. ) in a time lagged manner.

###### Q2. What have the authors stated for future works in "Share market sectoral indices movement forecast with lagged correlation and association rule mining" ?

This correlation can be exploited to predict the future index movement direction with a forecast horizon of d days where d is the number of day lag considered. 8. Future work will include analysis considering all sectors at a time instead of only a single sector predicts another. Hence this model can be used by different investors in balancing their portfolio to minimize risk as well as in deciding which sector to invest next. This model can be considered for short term investment as only prediction of next few d ys is possible using current d y ‘ s sector l index movements.

###### Q3. How can the authors use this model to predict the sectoral index movement?

Artificial neural network models can also be considered in combination with association rules to predict the sectoral index movement.

###### Q4. What is the earliest stock exchange in india?

The BombayStock Exchange (BSE) is one of the oldest stock exchanges in India and one of thetop stock exchanges globally with respect to number of listed companies and marketcapitalization.

###### Q5. What is the importance of association rule mining?

Data mining, an important part of knowledge discovery in databases (KDD) pro-cess employs many different techniques for knowledge discovery and prediction suchas classification, clustering, sequential pattern mining, association rule mining andanalysis.

###### Q6. What is the definition of technical analysis?

Technical analysis is done based on a lot of different technical indicator parameterssuch s ‗n-d ys moving ver ge‘ (where ‗n‘ c n be 5/10/20/50 etc. d ys), ‗n-daysweighted ver ge‘, MACD, relative strength index, momentum etc. along with price-to-earnings ratio, dividend yield, profit margin , return on investment etc.[2,3,12,15].

###### Q7. What are the main methods used for stock forecasting?

Rusu et al. discussed stock forecasting [14] methods used by classical approaches such as fundamentalists and chartists and at the same time discussed various recent stochastic methods like white noise, random walk, auto-regressive models etc.

###### Q8. What is the basic idea behind technical analysis?

The basic idea behind technical analy-sis is that current stock price of a company incorporates impacts and effects of eco-nomic, financial, political and psychological factors.

###### Q9. What is the co-variance between the two series?

If the authors consider alag of d days between them then co-variance between the two series is defined as-∑where μX and μY are the sample means of the time series X and Y.

###### Q10. What is the reason why auto index movements were low during the year 2015?

Auto index movements were very low during the year 2015 than all other sectors and it again can be attributed to non-reduction of car loan interest rates during the year.

###### Q11. What is the correlation coefficient of some sectors?

Results shows that some sectors are completely un-correlated but some are highly correlated (positively or negatively) with correlation coefficient values more than 0.8.

###### Q12. how many sectors are correlated with each other?

Correl tion with del y of ‗d‘ d ys is c lcul ted s the correl tion between the twodata arrays X,Y as below:xy = Correlation between X {p1,p2…pn} and Y{p1+d, p2+d,… pn+d}So the authors have a total of 15 sector pair from 6 sectors considered and for each pair wehave a total of 6 correlation values (with 0 day to 5 days of lag).

###### Q13. Why is the future stock price of a company stochastic?

Future stock price of a company becomes stochastic due to difference in perceptionabout the future of the company among investors.