Week 19 and 20 : 1/11/2018-16/11/2018

-

Time Series Forecasting

We had sessions with our mentor Varun Goel from Tatras,Delhi throughout the week and so on different techniques used in forecasting.
We covered following topics in these sessions:
●Forecasting – Introduction
●Linear Regression
●Moving Averages
●Exponential Smoothing
●ARMA, ARIMA

●Neural Networks, BRANNs

What is forecasting?

Forecast: (verb) to calculate or predict (some future event or condition) usually as a result of study and analysis of available pertinent data
Things we forecast…
–Weather parameters
–Sales numbers/ Demand
–Agricultural Production
–Currency exchange rates, Stock prices, Gold prices, Interest rates
–Internet Traffic
–Loss due to Epidemics and Natural Disasters and wars

Forecasting for  a Stationary Time Series

A stationary time series has the form: Dt = m + e t , where m is a constant and e t is a random variable with mean 0 and var σ2 

Methods:

●Naive Method
●Moving Averages
●Weighted Moving Averages

Simple exponential smoothening

          


Holt-Winter's Method - When Trend and seasonality are present















All the concepts and algorithms were then implemented in python.
An example snippet is shown below: 



OUTPUT:



Traffic police interaction

Along with learning time series forecasting,we also had interaction with Punjab traffic police personnel and they shared with us some projects and ideas they would like us to work upon in the future and various points were discussed. We started working on a mobile application also for them.
Location: Sahibzada Ajit Singh Nagar, Punjab, India

Comments

Post a Comment

Popular posts from this blog

Day 1 - Numpy Revision

-
Numpy Revision  We made a python program for the following random walk question: Say you are standing at the bottom of a staircase with a dice. With each throw of the dice, you either move down one step (if you get a 1 or 2 on the dice) or move up one step (if you get a 3, 4 or 5 on the dice). If you throw a 6 on the dice, you throw the dice again and move up the staircase by the number you get on that second throw. Note if you are on the base of the staircase you cannot move down! What is the probability that you will reach more than 60 steps after 250 throws of the dice? This question required the knowledge of np.random.seed. It s eeds the generator.  It makes the random numbers predictable. When the value is reset, the same numbers will appear every time. If a  seed is  not assigned , NumPy automatically selects a random seed value based on the system's random number generator device or on the clock The code was as follows: import numpy as np np.random.seed(1
Read more

Week 22 (26/11/18 - 30/11/18)

-
Lecture - Design Thinking This week we had a session with Mandeep Singh Kwatria on Design Thinking to help thinking about good innovative ideas. Design Thinking is a design methodology that provides a solution-based approach to solving problems. It’s extremely useful in tackling complex problems that are ill-defined or unknown, by understanding the human needs involved, by re-framing the problem in human-centric ways, by creating many ideas in brainstorming sessions, and by adopting a hands-on approach in prototyping and testing. The three Design Thinking Phases are: Inspire Ideate Implement   A ground-breaking innovation will be desirable, feasible and viable. Paddy Crop Project Along with other work, we also had a project from one of our professors related to paddy (confidential) which we worked on using the knowledge we got in this internship.
Read more

Week 18 (29/10/2018 - 02/11/2018)

-
Image
Ropar's Accident data Our company was given Ropar's Accident data by the Government to analyze and submit insights from the data that could be helpful to the government for reducing the number of serious accidents. We analyzed the data by using Tableau with the help of pie charts, histograms, etc. We also made dashboards and stories which gave us a really good insight of the data.   Convolutional Neural Networks We referred to the CMU's course on deep learning for understanding this concept.This lecture was taught by Bhiksha Raj Sir. CNNs, like neural networks, are made up of neurons with learnable weights and biases. Each neuron receives several inputs, takes a weighted sum over them, pass it through an activation function and responds with an output. Unlike neural networks, where the input is a vector, here the input is a multi-channeled image. The wholw network has a loss function. CNNs have wide applications in image and video recognition, re
Read more