## Table of contents

### No headings in the article.

Enhancing a model performance can be challenging at times. I’m sure, a lot of you would agree with me if you’ve found yourself stuck in a similar situation. You try all the strategies and algorithms that you’ve learned. Yet, you fail at improving the accuracy of your model. You feel helpless and stuck. And, this is where 90% of the data scientists give up.

But, this is where the real story begins! This is what differentiates an average data scientist from a master data scientist. Do you also dream of becoming a master data scientist ?

If yes, you need these 8 proven ways to re-structure your model approach. A predictive model can be built in many ways. There is no ‘must-follow’ rule. But, if you follow my ways (shared below), you’d surely achieve high accuracy in your models (given that the data provided is sufficient to make predictions).

I’ve learnt these methods with experience. I’ve always preferred to learn practically than digging theories. And, my approach has always encouraged me. In this article, I’ve shared the some of the proven ways using which you can create a robust machine learning model. I hope my knowledge can help people in achieving great heights in their careers.

The model development cycle goes through various stages, starting from data collection to model building.

But, before exploring the data to understand relationships (in variables), It’s always recommended to perform hypothesis generation. I believe this is the most under – rated step of predictive modeling.

It is important that you spend time thinking on the given problem and gaining the domain knowledge. So, how does it help?

This practice usually helps in building better features later on, which are not biased by the data available in the data-set. This is a crucial step which usually improves a model’s accuracy.

At this stage, you are expected to apply structured thinking to the problem i.e. a thinking process which takes into consideration all the possible aspects of a particular problem.

Let’s dig deeper now. Now we’ll check out the proven way to improve the accuracy of a model:

**1. Add more data**

Having more data is always a good idea. It allows the “data to tell for itself,” instead of relying on assumptions and weak correlations. Presence of more data results in better and accurate models.

I understand, we don’t get an option to add more data. For example: we do not get a choice to increase the size of training data in data science competitions. But while working on a company project, I suggest you to ask for more data, if possible. This will reduce your pain of working on limited data sets.

**2. Treat missing and Outlier values**

The unwanted presence of missing and outlier values in the training data often reduces the accuracy of a model or leads to a biased model. It leads to inaccurate predictions. This is because we don’t analyse the behavior and relationship with other variables correctly. So, it is important to treat missing and outlier values well.

Look at the below snapshot carefully. It shows that, in presence of missing values, the chances of playing cricket by females is similar as males. But, if you look at the second table (after treatment of missing values based on salutation of name, “Miss” ), we can see that females have higher chances of playing cricket compared to males.

**3. Feature Engineering**

This step helps to extract more information from existing data. New information is extracted in terms of new features. These features may have a higher ability to explain the variance in the training data. Thus, giving improved model accuracy.

Feature engineering is highly influenced by hypotheses generation. Good hypothesis result in good features. That’s why, I always suggest to invest quality time in hypothesis generation. Feature engineering process can be divided into two steps:

**Feature transformation: **There are various scenarios where feature transformation is required:
A) Changing the scale of a variable from original scale to scale between zero and one. This is known as data normalization. For example: If a data set has 1st variable in meter, 2nd in centi-meter and 3rd in kilo-meter, in such case, before applying any algorithm, we must normalize these variable in same scale.
B) Some algorithms works well with normally distributed data. Therefore, we must remove skewness of variable(s). There are methods like log, square root or inverse of the values to remove skewness.

C) Sometimes, creating bins of numeric data works well, since it handles the outlier values also. Numeric data can be made discrete by grouping values into bins. This is known as data discretization.

**Feature Creation:** Deriving new variable(s ) from existing variables is known as feature creation. It helps to unleash the hidden relationship of a data set. Let’s say, we want to predict the number of transactions in a store based on transaction dates. Here transaction dates may not have direct correlation with number of transaction, but if we look at the day of a week, it may have a higher correlation. In this case, the information about day of a week is hidden. We need to extract it to make the model better.

**4. Feature Selection**

Feature Selection is a process of finding out the best subset of attributes which better explains the relationship of independent variables with target variable.

You can select the useful features based on various metrics like:

Domain Knowledge: Based on domain experience, we select feature(s) which may have higher impact on target variable.

Visualization: As the name suggests, it helps to visualize the relationship between variables, which makes your variable selection process easier.

Statistical Parameters: We also consider the p-values, information values and other statistical metrics to select right features. PCA: It helps to represent training data into lower dimensional spaces, but still characterize the inherent relationships in the data. It is a type of dimensionality reduction technique. There are various methods to reduce the dimensions (features) of training data like factor analysis, low variance, higher correlation, backward/ forward feature selection and others.

**5. Multiple algorithms**

Hitting at the right machine learning algorithm is the ideal approach to achieve higher accuracy. But, it is easier said than done.

This intuition comes with experience and incessant practice. Some algorithms are better suited to a particular type of data sets than others. Hence, we should apply all relevant models and check the performance.

**6. Algorithm Tuning**

We know that machine learning algorithms are driven by parameters. These parameters majorly influence the outcome of the learning process.

The objective of parameter tuning is to find the optimum value for each parameter to improve the accuracy of the model. To tune these parameters, you must have a good understanding of these meanings and their individual impact on the model. You can repeat this process with a number of well-performing models.

For example: In random forest, we have various parameters like max_features, number_trees, random_state, oob_score, and others. Intuitive optimization of these parameter values will result in better and more accurate models.

**7. Ensemble methods**

This is the most common approach found majorly in winning solutions of Data science competitions. This technique simply combines the result of multiple weak models and produce better results. This can be achieved through many ways:

- Bagging (Bootstrap Aggregating)
- Boosting

It is always a better idea to apply ensemble methods to improve the accuracy of your model. There are two good reasons for this: a ) They are generally more complex than traditional methods. b) The traditional methods give you a good base level from which you can improve and draw from to create your ensembles.

**8. Cross Validation:**

To find the right answer of this question, we must use cross validation technique. Cross Validation is one of the most important concepts in data modeling. It says, try to leave a sample on which you do not train the model and test the model on this sample before finalizing the model. This method helps us to achieve more generalized relationships.

If you find this blog helpful, please do give it a like and share it with everyone.

Keep Learning New Stuffs Everyday! Happ Learning!